Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b4d76feea82e690074be4bc80f77367e279d87a1094bbfed0d27d37555f98
+oid sha256:68a3db55048747a77df96e815cd39f0628d6392eee3c772bc03cc66fdc44377f
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78525d18687b485c1892fdcdc92bdceb5339f5211cd093cb1a4923c0ef205a8b
+oid sha256:0b72681de3f7feb6d0293c2d75335f09214a81098511a5c6f24ee2efed77eb33
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee790821cfacd40e06956c8512b638420db8f108a42084c73e5fe8ec6bda6db3
+oid sha256:2154f4b0a77c0d8624f684d8a1b51d4c6f23e91091f55fb27f2ac18f98bd39b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015655577299412915,
+  "epoch": 0.023483365949119372,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 54.973,
       "eval_steps_per_second": 27.486,
       "step": 6
+    },
+    {
+      "epoch": 0.0182648401826484,
+      "grad_norm": 0.5827949643135071,
+      "learning_rate": 0.00014,
+      "loss": 2.3452,
+      "step": 7
+    },
+    {
+      "epoch": 0.020874103065883887,
+      "grad_norm": 0.5860369205474854,
+      "learning_rate": 0.00016,
+      "loss": 2.9203,
+      "step": 8
+    },
+    {
+      "epoch": 0.023483365949119372,
+      "grad_norm": 0.5119990110397339,
+      "learning_rate": 0.00018,
+      "loss": 2.3547,
+      "step": 9
+    },
+    {
+      "epoch": 0.023483365949119372,
+      "eval_loss": 2.6998348236083984,
+      "eval_runtime": 2.9584,
+      "eval_samples_per_second": 54.759,
+      "eval_steps_per_second": 27.38,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38579231784960.0,
+  "total_flos": 58297505808384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null