Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00248ee9684c65a32615da2b0cccb3ee6b6ac475e02b1cc704d4a10d03c53364
+oid sha256:1b6216de9a9a462c0f0a9760a790376ca0e539973c7f3826463aebf6c97ec1c0
 size 1476713628

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f8175b7a9c4f54cd8420af1fc659bf71ac2b603ae7671b17572d14702dc17b
+oid sha256:1489c6e698db88641cd49705df635a9e74211106f22d663f3575f13968f4b663
 size 2953659629

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c230ad29373d00210d983f3964cf3edad2620215c1c6091bf41cb911b3b787
+oid sha256:417d4aa9a3dc529c8f1781c2f4ecb82047727c7d9c79dcb7ecb2cf6784fb1ab9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a642fd3959d962a047731abaf128bced517e3db0e7e9f18577cfe93e2f6753
+oid sha256:37775b8eeac0cb3f10692b89524fddb6161b30fd23bb76e283dbca1e64da52f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7291361639824304,
-  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-199",
-  "epoch": 4.0,
+  "best_metric": 0.7459736456808199,
+  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-248",
+  "epoch": 4.984924623115578,
   "eval_steps": 500,
-  "global_step": 199,
+  "global_step": 248,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,6 +43,15 @@
       "eval_samples_per_second": 30.072,
       "eval_steps_per_second": 3.764,
       "step": 199
+    },
+    {
+      "epoch": 4.984924623115578,
+      "eval_accuracy": 0.7459736456808199,
+      "eval_loss": 0.59873366355896,
+      "eval_runtime": 46.355,
+      "eval_samples_per_second": 29.468,
+      "eval_steps_per_second": 3.689,
+      "step": 248
     }
   ],
   "logging_steps": 500,
@@ -62,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.182275420448384e+16,
+  "total_flos": 1.47784427556048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null