Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1a85d4adbb15ef1b94928b605d155dd95acc518e22c2e6eb72290efc2f7e63
+oid sha256:5e27643d9b8bf05c2b5b9f5507eb1a2dbf6003af1b60080b9b807aa553c24355
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1d6a4b7778e6b9851702fb4935100f335c1eb1a12d8d5933a9660392aa45e3
+oid sha256:eec1df1eb87cf88834f95c8cb0154c659270dead40118d922f3e0dc368ceac2c
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5911fb24845bf0d03bb4ed0de81ea57c74b908d85c6fbc986d4f2cc0c1e66086
+oid sha256:d39ca3c79bf555f45a0bf62da054b00292a0fbc4c86058b7edd94e9f36dfdd3e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d724bb510d94705e657796ece24064ce1b4bac1fa49b16ccd5fbb9a62a4acb8
+oid sha256:9ac017a31e7650c8ad53026306c46f4f88cda43e2e318ec95a03068a6ea46af5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6995002361282292,
-  "best_model_checkpoint": "training_dir/checkpoint-6000",
-  "epoch": 2.949852507374631,
+  "best_metric": 0.7086352031822583,
+  "best_model_checkpoint": "training_dir/checkpoint-10000",
+  "epoch": 3.2776138970829236,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -178,6 +178,25 @@
       "eval_samples_per_second": 46.469,
       "eval_steps_per_second": 5.809,
       "step": 9000
+    },
+    {
+      "epoch": 3.2776138970829236,
+      "grad_norm": 67.79216766357422,
+      "learning_rate": 6.834388537154283e-06,
+      "loss": 0.3539,
+      "step": 10000
+    },
+    {
+      "epoch": 3.2776138970829236,
+      "eval_accuracy": 0.7194055944055944,
+      "eval_f1": 0.7086352031822583,
+      "eval_loss": 1.335507869720459,
+      "eval_precision": 0.7194188784778419,
+      "eval_recall": 0.7194055944055944,
+      "eval_runtime": 49.1977,
+      "eval_samples_per_second": 46.506,
+      "eval_steps_per_second": 5.813,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -197,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6210645251958756.0,
+  "total_flos": 6894084410080812.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null