Training in progress, epoch 6

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f416b06624d5c0d9c88fef618f495f3388aabde44fd315d4840e248486442a6
+oid sha256:1efac210aef14a836eb8349cce523c66e2d6fa5a154e59184f0b9fac6a1455c0
 size 598898116

run-0/checkpoint-720/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4978a36c2bfa514c88e7d77522720cbd803b0a220428a29701d116615b89f8
+oid sha256:1efac210aef14a836eb8349cce523c66e2d6fa5a154e59184f0b9fac6a1455c0
 size 598898116

run-0/checkpoint-720/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568847898d617e33aee75b1974a224f130cca253f6b7d8348831c5432289079d
+oid sha256:ccc361d9ba19744a8fac05c2041365476665d92b97a6be454d52ff012130de0b
 size 1197886411

run-0/checkpoint-720/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5995efe96d9a5f379fc424e908527d23598b0bf812a8ecdac188a585ddec1b05
+size 1383

run-0/checkpoint-720/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 600,
-  "best_metric": 0.9441935483870968,
-  "best_model_checkpoint": "student_modernBERT_clinc_oos/run-0/checkpoint-600",
+  "best_global_step": 720,
+  "best_metric": 0.9245161290322581,
+  "best_model_checkpoint": "student_modernBERT_clinc_oos/run-0/checkpoint-720",
   "epoch": 6.0,
   "eval_steps": 500,
   "global_step": 720,
@@ -11,63 +11,63 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.792258064516129,
-      "eval_loss": 5.377152442932129,
-      "eval_runtime": 8.5979,
-      "eval_samples_per_second": 360.552,
-      "eval_steps_per_second": 11.282,
+      "eval_accuracy": 0.5541935483870968,
+      "eval_loss": 1.7238802909851074,
+      "eval_runtime": 7.0038,
+      "eval_samples_per_second": 442.616,
+      "eval_steps_per_second": 13.85,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9112903225806451,
-      "eval_loss": 1.624509572982788,
-      "eval_runtime": 8.6846,
-      "eval_samples_per_second": 356.952,
-      "eval_steps_per_second": 11.169,
+      "eval_accuracy": 0.8570967741935483,
+      "eval_loss": 1.1208338737487793,
+      "eval_runtime": 6.8486,
+      "eval_samples_per_second": 452.646,
+      "eval_steps_per_second": 14.163,
       "step": 240
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.9387096774193548,
-      "eval_loss": 0.9765816926956177,
-      "eval_runtime": 8.7254,
-      "eval_samples_per_second": 355.283,
-      "eval_steps_per_second": 11.117,
+      "eval_accuracy": 0.9051612903225806,
+      "eval_loss": 0.9070075154304504,
+      "eval_runtime": 6.8675,
+      "eval_samples_per_second": 451.403,
+      "eval_steps_per_second": 14.125,
       "step": 360
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9412903225806452,
-      "eval_loss": 0.799368679523468,
-      "eval_runtime": 8.7525,
-      "eval_samples_per_second": 354.185,
-      "eval_steps_per_second": 11.083,
+      "eval_accuracy": 0.9164516129032259,
+      "eval_loss": 0.8145634531974792,
+      "eval_runtime": 6.8676,
+      "eval_samples_per_second": 451.395,
+      "eval_steps_per_second": 14.124,
       "step": 480
     },
     {
       "epoch": 4.167714884696017,
-      "grad_norm": 16.940773010253906,
+      "grad_norm": 6.844017505645752,
       "learning_rate": 6.13888888888889e-06,
-      "loss": 15.9509,
+      "loss": 5.4805,
       "step": 500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9441935483870968,
-      "eval_loss": 0.7491059899330139,
-      "eval_runtime": 8.7187,
-      "eval_samples_per_second": 355.557,
-      "eval_steps_per_second": 11.125,
+      "eval_accuracy": 0.9219354838709677,
+      "eval_loss": 0.7720023989677429,
+      "eval_runtime": 6.8461,
+      "eval_samples_per_second": 452.813,
+      "eval_steps_per_second": 14.169,
       "step": 600
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9435483870967742,
-      "eval_loss": 0.7189788818359375,
-      "eval_runtime": 8.7026,
-      "eval_samples_per_second": 356.214,
-      "eval_steps_per_second": 11.146,
+      "eval_accuracy": 0.9245161290322581,
+      "eval_loss": 0.7577660083770752,
+      "eval_runtime": 6.835,
+      "eval_samples_per_second": 453.548,
+      "eval_steps_per_second": 14.192,
       "step": 720
     }
   ],
@@ -92,8 +92,8 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.34970567105973893,
+    "alpha": 0.17839594203233045,
     "num_train_epochs": 6,
-    "temperature": 2
+    "temperature": 13
   }
 }

run-0/checkpoint-720/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a14a0ccc0ae09af707f7c86d234da20596840e059e696e004c12f6a9fa0185
+oid sha256:defea8818495be5704f8f89261e105141cdc7770477d9f23e5c577ed2e3f7868
 size 5905

runs/Oct26_17-22-45_49ca29516c75/events.out.tfevents.1761500015.49ca29516c75.609.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2b0505116aa438a0cf29708e2f0148a0a7f0a4b35c0f9a653554bf943994da
-size 15041
+oid sha256:f41c254dc090469b35f8a4d9a7bcc851a64bd7ca9b81cdea3b3c2426806f6cc9
+size 15718