Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90481225a3d7774ba32f5b8f7c775a1bcfa17416d19927c4d27b19d74e42c88
+oid sha256:3746e89ab4ed2d2714cec87011941709b73dd81893768c249c061126dbe2aff0
 size 498625128

run-1/checkpoint-1128/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7990e33fa8b696609893e535a2f57fb904b216de13b4775c66d8ed0932dc14c
+oid sha256:3746e89ab4ed2d2714cec87011941709b73dd81893768c249c061126dbe2aff0
 size 498625128

run-1/checkpoint-1128/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba389666a1538a58cab9c12a95eeeeeb5f4e71cb91ca95fdce47e6e6e2a545d
+oid sha256:dab24bf8d5cc95a11a7f2fb088ad62a6b1e9f79bb72eef0edbd1bd3c2f57f579
 size 997370106

run-1/checkpoint-1128/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff2d40c223213c363127db4770730073a9d8a9eb7817acc6eb31d3bab5782f5
+oid sha256:cd0a274913fef54a5fb0ef6bc05b6fdcfe47377f29f7951c26086f985ddf1784
 size 1064

run-1/checkpoint-1128/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6285243252934658,
+  "best_metric": 0.626596640291279,
   "best_model_checkpoint": "students_scores_model/run-1/checkpoint-1128",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,52 +10,52 @@
   "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
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.6179112498233506,
-      "eval_loss": 0.8894566893577576,
-      "eval_runtime": 37.6552,
-      "eval_samples_per_second": 59.753,
-      "eval_steps_per_second": 7.489,
+      "eval_f1": 0.60670227423826,
+      "eval_loss": 0.919843316078186,
+      "eval_runtime": 37.6908,
+      "eval_samples_per_second": 59.696,
+      "eval_steps_per_second": 7.482,
       "step": 846
     },
     {
       "epoch": 3.546099290780142,
-      "grad_norm": 19.25679588317871,
-      "learning_rate": 3.8466984971609285e-06,
-      "loss": 0.8051,
+      "grad_norm": 27.95517349243164,
+      "learning_rate": 6.617362010791962e-06,
+      "loss": 0.7766,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.6285243252934658,
-      "eval_loss": 0.8603602647781372,
-      "eval_runtime": 37.769,
-      "eval_samples_per_second": 59.573,
-      "eval_steps_per_second": 7.466,
+      "eval_f1": 0.626596640291279,
+      "eval_loss": 0.8775350451469421,
+      "eval_runtime": 37.7332,
+      "eval_samples_per_second": 59.629,
+      "eval_steps_per_second": 7.474,
       "step": 1128
     }
   ],
@@ -80,9 +80,9 @@
   "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-1128/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 sha256:41a1e666a2d688ac685d99cdfeb9a268e129fefe6b5aaa078732fa35a2d23b02
-size 6516
+oid sha256:8e6e2f8ce847222ebe53a8ebb020059460f25fbd45c826ccf27bed0d85b8ba7b
+size 7044