Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3dd6d80865c5fd05244ffe06dd84a55a85e5bc98378182798a66e1d72e79ac
+oid sha256:6d2029ee79548859acc224628ab89006bef1b9b070648298cb8efdef835313b3
 size 498625128

run-1/checkpoint-564/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f643cc05be2c21bafc32efbe159f00a47da0a25565448ce8c379a63886e58d
+oid sha256:6d2029ee79548859acc224628ab89006bef1b9b070648298cb8efdef835313b3
 size 498625128

run-1/checkpoint-564/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4440f807708d633821fa0bc2fad346fe133b23e594a2c08d2c650be3c31dc63e
+oid sha256:82c813451f999d8c0864892cd20565c62db960d07eb0f475b6867dedbe917ba7
 size 997370106

run-1/checkpoint-564/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d3add6080a2df6ed67a89b2c7d382e1530e83928233ed04ecd6f82c5f24349
+oid sha256:2df84efdcfa7492abc422bc3ba3194786661774ca9be35439e86b68040e794a4
 size 1064

run-1/checkpoint-564/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5853742204012189,
+  "best_metric": 0.5968612549522194,
   "best_model_checkpoint": "students_scores_model/run-1/checkpoint-564",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.5135559583730447,
-      "eval_loss": 1.0615456104278564,
-      "eval_runtime": 37.678,
-      "eval_samples_per_second": 59.716,
-      "eval_steps_per_second": 7.484,
+      "eval_f1": 0.49162421787585286,
+      "eval_loss": 1.09846031665802,
+      "eval_runtime": 37.7448,
+      "eval_samples_per_second": 59.611,
+      "eval_steps_per_second": 7.471,
       "step": 282
     },
     {
       "epoch": 1.773049645390071,
-      "grad_norm": 11.819360733032227,
-      "learning_rate": 8.537794225405964e-06,
-      "loss": 1.0289,
+      "grad_norm": 8.43077564239502,
+      "learning_rate": 1.4687315682489477e-05,
+      "loss": 1.0146,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.5853742204012189,
-      "eval_loss": 0.9459031224250793,
-      "eval_runtime": 37.7163,
-      "eval_samples_per_second": 59.656,
-      "eval_steps_per_second": 7.477,
+      "eval_f1": 0.5968612549522194,
+      "eval_loss": 0.9038913249969482,
+      "eval_runtime": 37.6284,
+      "eval_samples_per_second": 59.795,
+      "eval_steps_per_second": 7.494,
       "step": 564
     }
   ],
@@ -55,9 +55,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.3228889953650998e-05,
+    "learning_rate": 2.275726935418699e-05,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "weight_decay": 0.0004860339799795757
+    "weight_decay": 0.0002055903667746397
   }
 }

run-1/checkpoint-564/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
+oid sha256:5170867ff483caf9169cfca440571d2f9bf4863737851b36e8f14b28d996f499
 size 5368

runs/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733750185.ea67bac3fd95.23.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad2f20be6eb531e61790754d01c9bc1dcc77d6b42beb09c5e5d145e746fe657
-size 5671
+oid sha256:ce3912c8c0cf74e410e75bdc3b42bbf24402d1681a56a9d601ca2235dc257750
+size 6199