Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ea6143365bb1b955914e1894d1a9de3c8e82b53b2d92377c19fa703ff614cb
+oid sha256:b8b087d365f9b47bcb5ac8af147a7ce444d50256e0f588622fd8a7c4b178e62a
 size 498625128

run-0/checkpoint-1689/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17de67ad92dabf88985a54e46778d6c5d57f8027da6db3b5f37de0c6b94ff74b
+oid sha256:b8b087d365f9b47bcb5ac8af147a7ce444d50256e0f588622fd8a7c4b178e62a
 size 498625128

run-0/checkpoint-1689/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c48b13f56fb2a15d11eeb5145150b84f70944494eec88405255d80e4fcdee9
+oid sha256:59729c12013004750cb65b3640afab9eb6d6b96e9d2d269fdbf4552e3fe0ac90
 size 997370106

run-0/checkpoint-1689/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071c5e9be8c89f7e7601ef6e67c044701f3e899071b5431a452dcbeb2c3af0a4
+oid sha256:68f1d83a24dea24b3ee8fe08ca2d8c2be0524aab6848d54221b60f93a60135a4
 size 14244

run-0/checkpoint-1689/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80de0fe2308c3690dd22295d36b26938d5f0098babe16dede9fcbd27e598439d
+oid sha256:8e4b58894049dba5ecea76fd6426a18215864e341b6a3172f1c3fd8e0a5dbbbe
 size 1064

run-0/checkpoint-1689/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.622779879885066,
+  "best_metric": 0.625181470032157,
   "best_model_checkpoint": "students_scores_model/run-0/checkpoint-1689",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,50 +10,50 @@
   "log_history": [
     {
       "epoch": 0.8880994671403197,
-      "grad_norm": 9.486105918884277,
-      "learning_rate": 1.6060239187203855e-05,
-      "loss": 1.0687,
+      "grad_norm": 15.162298202514648,
+      "learning_rate": 1.1081212788560944e-05,
+      "loss": 1.0807,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.559496193541961,
-      "eval_loss": 1.0184900760650635,
-      "eval_runtime": 37.7502,
-      "eval_samples_per_second": 59.602,
-      "eval_steps_per_second": 7.47,
+      "eval_f1": 0.5653313080683391,
+      "eval_loss": 0.9786226153373718,
+      "eval_runtime": 37.7159,
+      "eval_samples_per_second": 59.657,
+      "eval_steps_per_second": 7.477,
       "step": 563
     },
     {
       "epoch": 1.7761989342806395,
-      "grad_norm": 16.897672653198242,
-      "learning_rate": 9.306564171558836e-06,
-      "loss": 0.8626,
+      "grad_norm": 24.097002029418945,
+      "learning_rate": 6.421325156701843e-06,
+      "loss": 0.8868,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.6141765793522762,
-      "eval_loss": 0.877347469329834,
-      "eval_runtime": 37.6032,
-      "eval_samples_per_second": 59.835,
-      "eval_steps_per_second": 7.499,
+      "eval_f1": 0.6070480622856711,
+      "eval_loss": 0.8847860097885132,
+      "eval_runtime": 37.644,
+      "eval_samples_per_second": 59.771,
+      "eval_steps_per_second": 7.491,
       "step": 1126
     },
     {
       "epoch": 2.664298401420959,
-      "grad_norm": 14.929506301879883,
-      "learning_rate": 2.552889155913817e-06,
-      "loss": 0.7589,
+      "grad_norm": 11.891419410705566,
+      "learning_rate": 1.7614375248427405e-06,
+      "loss": 0.7962,
       "step": 1500
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.622779879885066,
-      "eval_loss": 0.8738921880722046,
-      "eval_runtime": 38.6362,
-      "eval_samples_per_second": 58.236,
-      "eval_steps_per_second": 7.299,
+      "eval_f1": 0.625181470032157,
+      "eval_loss": 0.87553471326828,
+      "eval_runtime": 38.7494,
+      "eval_samples_per_second": 58.065,
+      "eval_steps_per_second": 7.278,
       "step": 1689
     }
   ],
@@ -78,9 +78,9 @@
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.2813914202848873e-05,
+    "learning_rate": 1.5741100420420047e-05,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 16,
-    "weight_decay": 0.0012064342197859815
+    "weight_decay": 0.06367619176381757
   }
 }

run-0/checkpoint-1689/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e506878344e67934428f3176c568da4bb4fdfd8b8918c71494a2c9eb08433b
+oid sha256:2d79a0a1b1999dd0f4d771c0a4c6c2e334edf8b223fe42e75cbf50a67fc6c2de
 size 5368

runs/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733748065.ea67bac3fd95.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94897b1553c80b0d65888b8e664fb3a6ad62dc3aceab4d7d97de979095b887e1
-size 6428
+oid sha256:4a8eb11f2865b9a7b2d36c666ed0103b6464a718040f159b71a69474b09a27d1
+size 6639