Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161429549ad046c92c0830348f3519a81c9695140c076ba86819b63651deff64
+oid sha256:77ebea82a9f3c4e22e3f17a10fe0983aceb8b905574bf779f0d1f4afcb2c2589
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303573cf617fd5524986ae8dd755826ae69c14b6d66df9a27c6e00700c7f2ce6
+oid sha256:b69147daac578b55f7fb85920e4fed94f30a35f561e7324d1f02402b279bf900
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47899d438bc1e8e9d368d92fe5b1946e59435e7701dd92edc87bdef54734dd67
+oid sha256:6cf31f3315e0bfe25fcfad59fbf87799e20f6322db5e15fc401b772537e73d62
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11342b2430a338f69f1320c6f8235ca7935daec91992c25666791c4e55f7a3d9
+oid sha256:35fe87dbd6014deea326105569abe0f140270c203f324b3dec6bdad30aaebd26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6211330799726014,
-  "best_model_checkpoint": "training_dir/checkpoint-1000",
-  "epoch": 4.0,
+  "best_metric": 0.6631765774552385,
+  "best_model_checkpoint": "training_dir/checkpoint-1250",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -83,6 +83,25 @@
       "eval_samples_per_second": 46.969,
       "eval_steps_per_second": 5.871,
       "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.5804481506347656,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.3592,
+      "step": 1250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6765734265734266,
+      "eval_f1": 0.6631765774552385,
+      "eval_loss": 1.30519437789917,
+      "eval_precision": 0.6758934188659348,
+      "eval_recall": 0.6765734265734266,
+      "eval_runtime": 48.2801,
+      "eval_samples_per_second": 47.39,
+      "eval_steps_per_second": 5.924,
+      "step": 1250
     }
   ],
   "logging_steps": 500,
@@ -102,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1668780407351232.0,
+  "total_flos": 2086004287219104.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null