Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771fe01e68dea441f9d1f001f494502b2924afcf69501e14bed2d8bbf7f7e041
+oid sha256:17de67ad92dabf88985a54e46778d6c5d57f8027da6db3b5f37de0c6b94ff74b
 size 498625128

run-0/checkpoint-1689/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d424baca1f38454e3775f28b9e517a78fa49193e015b4b962eab43e03d9598
+oid sha256:17de67ad92dabf88985a54e46778d6c5d57f8027da6db3b5f37de0c6b94ff74b
 size 498625128

run-0/checkpoint-1689/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec17437bbf50835b03bfda15542a12196060b091f06fa0b85aea2de73a33530
+oid sha256:18c48b13f56fb2a15d11eeb5145150b84f70944494eec88405255d80e4fcdee9
 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 sha256:88a4db435e7ca3c38de2f68b620cf2cd96c6eaca2cd61476c3769575994680ca
+oid sha256:80de0fe2308c3690dd22295d36b26938d5f0098babe16dede9fcbd27e598439d
 size 1064

run-0/checkpoint-1689/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.623488690122392,
+  "best_metric": 0.622779879885066,
   "best_model_checkpoint": "students_scores_model/run-0/checkpoint-1689",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,57 +10,57 @@
   "log_history": [
     {
       "epoch": 0.8880994671403197,
-      "grad_norm": 7.708984851837158,
-      "learning_rate": 1.9955684198991877e-05,
-      "loss": 1.084,
+      "grad_norm": 9.486105918884277,
+      "learning_rate": 1.6060239187203855e-05,
+      "loss": 1.0687,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.5481089178399972,
-      "eval_loss": 1.059887409210205,
-      "eval_runtime": 37.3909,
-      "eval_samples_per_second": 60.175,
-      "eval_steps_per_second": 7.542,
+      "eval_f1": 0.559496193541961,
+      "eval_loss": 1.0184900760650635,
+      "eval_runtime": 37.7502,
+      "eval_samples_per_second": 59.602,
+      "eval_steps_per_second": 7.47,
       "step": 563
     },
     {
       "epoch": 1.7761989342806395,
-      "grad_norm": 15.52182388305664,
-      "learning_rate": 1.4260568845398305e-05,
-      "loss": 0.8598,
+      "grad_norm": 16.897672653198242,
+      "learning_rate": 9.306564171558836e-06,
+      "loss": 0.8626,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.6105817176137399,
-      "eval_loss": 0.8904849290847778,
-      "eval_runtime": 37.5314,
-      "eval_samples_per_second": 59.95,
-      "eval_steps_per_second": 7.514,
+      "eval_f1": 0.6141765793522762,
+      "eval_loss": 0.877347469329834,
+      "eval_runtime": 37.6032,
+      "eval_samples_per_second": 59.835,
+      "eval_steps_per_second": 7.499,
       "step": 1126
     },
     {
       "epoch": 2.664298401420959,
-      "grad_norm": 14.333279609680176,
-      "learning_rate": 8.565453491804732e-06,
-      "loss": 0.7595,
+      "grad_norm": 14.929506301879883,
+      "learning_rate": 2.552889155913817e-06,
+      "loss": 0.7589,
       "step": 1500
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.623488690122392,
-      "eval_loss": 0.9218708872795105,
-      "eval_runtime": 37.7188,
-      "eval_samples_per_second": 59.652,
-      "eval_steps_per_second": 7.476,
+      "eval_f1": 0.622779879885066,
+      "eval_loss": 0.8738921880722046,
+      "eval_runtime": 38.6362,
+      "eval_samples_per_second": 58.236,
+      "eval_steps_per_second": 7.299,
       "step": 1689
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2252,
+  "max_steps": 1689,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -69,18 +69,18 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6573013331208192.0,
+  "total_flos": 6310155946881024.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.565079955258545e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 2.2813914202848873e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 16,
-    "weight_decay": 0.003210706404646112
+    "weight_decay": 0.0012064342197859815
   }
 }

run-0/checkpoint-1689/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525778a4bf55e74b3e05d86fa160c25920ec80c82219483d314284448f6893fa
+oid sha256:86e506878344e67934428f3176c568da4bb4fdfd8b8918c71494a2c9eb08433b
 size 5368

runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733664606.3b937233628b.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b973d203d8ac28b889c478599817814407e9f612651b735c0761d649db2e43
-size 6430
+oid sha256:e96c87fba5c9f879263c9f22eb08bf65b18a48b87749d9c5bc0be73fec0f7477
+size 6641