Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b01318f5956c448c98fe80d37e937bff96ac48b70bf1609065a70531d1bf86
+oid sha256:e9245b2a2111c2f10b9cac642ac35c3985760aca66c25c677cf920b96ca46e32
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c293dc67c4b1440326792f82a1e72b876364aa32d07810da1f6968afb9b35fcb
+oid sha256:40ba40ef754c2e1e76672c2b441276a9122c592e0da78d0e656f178491ff3ed2
 size 5561082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a3f1b8b4f79ba1efde81b2b64b3deb3bea2f7b8fb6321e67464013e5ab9740
+oid sha256:83c2b2ba8d50beadd3437ad7c29560b3f39b33e50376d8025c855d91e6bb97d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013293943870014771,
+  "epoch": 0.014771048744460856,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 6.571,
       "eval_steps_per_second": 3.285,
       "step": 9
+    },
+    {
+      "epoch": 0.014771048744460856,
+      "grad_norm": 70.41092681884766,
+      "learning_rate": 0.0002,
+      "loss": 22.0738,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 155200757170176.0,
+  "total_flos": 172445285744640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null