Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05da4069fc52d58f023e29df4dcdd61eef9ec8db8396ec64e56917963bbb9d9
+oid sha256:bf658bcb3d6e926ee8e4606c9b8822870aeb69f28f4d04ca4eeb4ef7b23b422c
 size 598898116

run-0/checkpoint-636/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d34bdf3ceb775f7abffb8b735fee41b5a8dd68734961c8b0d8b0ea59b85b35c
+oid sha256:bf658bcb3d6e926ee8e4606c9b8822870aeb69f28f4d04ca4eeb4ef7b23b422c
 size 598898116

run-0/checkpoint-636/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e806e352a23a7f796f9affbdeff3dde5a2ae4aa62f4d76ab0613a13166ed188d
+oid sha256:aa9b8bf2bab7a8a5591b66774d44bd2a63a1855204d0243b34371f380038a837
 size 1197886411

run-0/checkpoint-636/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edf381b4ea3ddb40e833d7627fcf7989bb19d7093095cfc21fcbe490bc46ba5
+oid sha256:f46bd5e01fd050f0b60b6f6b624c2b4bbdecaf3740e9bbb0744d423f91c08a4b
 size 1383

run-0/checkpoint-636/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897f0481850fa5341e40153cf6dcf6d03b540ee8cbb8de088c3f76164e5df9c4
+oid sha256:fff711eebd4297f4d30bcd2f761d370446defe74842dbd45de3421b9f4e097b3
 size 1465

run-0/checkpoint-636/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 636,
-  "best_metric": 0.919790351277775,
+  "best_metric": 0.9414720571915698,
   "best_model_checkpoint": "ModernBERT-base-distilled/run-0/checkpoint-636",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,43 +11,43 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 6.882817268371582,
-      "learning_rate": 1.0031446540880504e-05,
-      "loss": 3.7921,
+      "grad_norm": 7.095359802246094,
+      "learning_rate": 1.5015723270440253e-05,
+      "loss": 4.2443,
       "step": 318
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8806451612903226,
-      "eval_f1": 0.8782099185536261,
-      "eval_loss": 2.21335768699646,
-      "eval_runtime": 19.6251,
-      "eval_samples_per_second": 157.961,
-      "eval_steps_per_second": 3.312,
+      "eval_accuracy": 0.9070967741935484,
+      "eval_f1": 0.9051373620810793,
+      "eval_loss": 2.06101655960083,
+      "eval_runtime": 16.6455,
+      "eval_samples_per_second": 186.236,
+      "eval_steps_per_second": 3.905,
       "step": 318
     },
     {
       "epoch": 2.0,
-      "grad_norm": 5.356029510498047,
-      "learning_rate": 3.1446540880503146e-08,
-      "loss": 1.8385,
+      "grad_norm": 6.176209449768066,
+      "learning_rate": 1.0015723270440252e-05,
+      "loss": 1.4635,
       "step": 636
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9209677419354839,
-      "eval_f1": 0.919790351277775,
-      "eval_loss": 1.6662155389785767,
-      "eval_runtime": 16.6015,
-      "eval_samples_per_second": 186.73,
-      "eval_steps_per_second": 3.915,
+      "eval_accuracy": 0.9425806451612904,
+      "eval_f1": 0.9414720571915698,
+      "eval_loss": 1.1604701280593872,
+      "eval_runtime": 16.5771,
+      "eval_samples_per_second": 187.005,
+      "eval_steps_per_second": 3.921,
       "step": 636
     }
   ],
   "logging_steps": 500,
-  "max_steps": 636,
+  "max_steps": 1272,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -65,17 +65,17 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 450992510607528.0,
+  "total_flos": 556619304143304.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.2238473023876273,
-    "num_train_epochs": 2,
-    "temperature": 16
+    "alpha": 0.362336107066899,
+    "num_train_epochs": 4,
+    "temperature": 10
   }
 }

run-0/checkpoint-636/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c288a49e5d462511afdcb18951b1fb2d83ef9f1ece8ef0108b7a3182e94fe32
+oid sha256:e57990bfcffc7508b1aa41cf9c14f9a33fd6a76ae0e5b564184c21c4e65e1398
 size 5905

runs/Oct11_19-55-54_cd07aeb3aeb4/events.out.tfevents.1760213687.cd07aeb3aeb4.2948.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8347db70977538ed9d9e433e8a4c4278244d3788ddfb49687a6c6c6eb814aae
-size 27492
+oid sha256:4325dfbf291448b9a1983f1cfad1c5aec6e8ea31c0fdf2bbb3ee2ec29d3515ed
+size 28072