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:f12bd95344c57d740664358adff5958ce2a07f39a83140769e7d57479186de31
+oid sha256:95b01318f5956c448c98fe80d37e937bff96ac48b70bf1609065a70531d1bf86
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1086093189d369e7a4e0cef79ed774fd3a8dde9c3112f5b35dc63da4d06dc35
+oid sha256:c293dc67c4b1440326792f82a1e72b876364aa32d07810da1f6968afb9b35fcb
 size 5561082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84fc8472545bafefa43e2daf6beb8da8cfe9e08e54bb28046afaeb3caf5b600
+oid sha256:69a3f1b8b4f79ba1efde81b2b64b3deb3bea2f7b8fb6321e67464013e5ab9740
 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": 0.008862629246676515,
+  "epoch": 0.013293943870014771,
   "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": 6.578,
       "eval_steps_per_second": 3.289,
       "step": 6
+    },
+    {
+      "epoch": 0.0103397341211226,
+      "grad_norm": 88.56855010986328,
+      "learning_rate": 0.00014,
+      "loss": 29.8127,
+      "step": 7
+    },
+    {
+      "epoch": 0.011816838995568686,
+      "grad_norm": 82.56781005859375,
+      "learning_rate": 0.00016,
+      "loss": 25.4548,
+      "step": 8
+    },
+    {
+      "epoch": 0.013293943870014771,
+      "grad_norm": 76.79576110839844,
+      "learning_rate": 0.00018,
+      "loss": 22.9964,
+      "step": 9
+    },
+    {
+      "epoch": 0.013293943870014771,
+      "eval_loss": 5.095368385314941,
+      "eval_runtime": 43.5257,
+      "eval_samples_per_second": 6.571,
+      "eval_steps_per_second": 3.285,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 103467171446784.0,
+  "total_flos": 155200757170176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null