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:e55a7a2800b11cf228e53ec4da7c02921ac6b50070abc0c356385c62a60209cd
+oid sha256:6c6e09b0cc56ae5d46b7af9912d522bde0e2725b423f1d237195c78ade513979
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea7fec12f6abd90de3b923e4424b11d10589b6961349f4d28737e695588c195
+oid sha256:861dc8a0277dd27ce677e55506fa10f0128612adb95c159fe97f333b4c2d3300
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b35cfe9f5e5f782238d2a3b603736aaf8ebd4736e7c2ce4d888cdf269bffaf77
+oid sha256:c56713b4b79a95f0ba69a6f670426dd06a01045e2bc2332f5ab3536d682a7b5b
 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": 0.00047070821974228727,
+  "epoch": 0.0007060623296134309,
   "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": 14.758,
       "eval_steps_per_second": 7.379,
       "step": 6
+    },
+    {
+      "epoch": 0.0005491595896993352,
+      "grad_norm": 0.7782320380210876,
+      "learning_rate": 0.00014,
+      "loss": 2.1435,
+      "step": 7
+    },
+    {
+      "epoch": 0.000627610959656383,
+      "grad_norm": 0.712628960609436,
+      "learning_rate": 0.00016,
+      "loss": 1.8562,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007060623296134309,
+      "grad_norm": 0.6478232741355896,
+      "learning_rate": 0.00018,
+      "loss": 2.147,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007060623296134309,
+      "eval_loss": 1.9906666278839111,
+      "eval_runtime": 363.6948,
+      "eval_samples_per_second": 14.76,
+      "eval_steps_per_second": 7.38,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2376205546291200.0,
+  "total_flos": 3590710603284480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null