Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a21ae3c9e3db79090f4ff9bbb5ab67d6c8d6949686493fa499c05e35af8cda2
+oid sha256:07e441f4986c665ba05c1436f3931b684f8a579a6f815d79e1e3ed27cb33e05a
 size 598898116

run-2/checkpoint-636/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd7bdef26f6b65507508637483b1b5872daf94543631344f6052c1b96e2b7c3
+oid sha256:07e441f4986c665ba05c1436f3931b684f8a579a6f815d79e1e3ed27cb33e05a
 size 598898116

run-2/checkpoint-636/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1f2b004904d99befa65b7cb0796986401ec5e2ccecea20e7e2540742c96b5b
+oid sha256:bb4e7ac45a45c238809fdc443a4013aa6512c6bc836699fc456ab3178a533410
 size 1197886411

run-2/checkpoint-636/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1227ec0ded90cf65dfb5e83b9af42af4a01a04951bd873a30191e8c9579bf4
+oid sha256:b342b565cc113c3c0d6c74f4134edc5cbad007e754b2134bf57179bf442ad650
 size 1383

run-2/checkpoint-636/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 636,
-  "best_metric": 0.9402146858730125,
+  "best_metric": 0.9386540826458253,
   "best_model_checkpoint": "ModernBERT-base-distilled/run-2/checkpoint-636",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,38 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 6.1552348136901855,
+      "grad_norm": 7.241408824920654,
       "learning_rate": 1.3354297693920338e-05,
-      "loss": 2.9367,
+      "loss": 3.1039,
       "step": 318
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9012903225806451,
-      "eval_f1": 0.8990202628613445,
-      "eval_loss": 1.5702729225158691,
-      "eval_model_preparation_time": 0.0029,
-      "eval_runtime": 17.5772,
-      "eval_samples_per_second": 176.365,
-      "eval_steps_per_second": 3.698,
+      "eval_accuracy": 0.9058064516129032,
+      "eval_f1": 0.9039413673060775,
+      "eval_loss": 1.5589689016342163,
+      "eval_runtime": 16.8256,
+      "eval_samples_per_second": 184.243,
+      "eval_steps_per_second": 3.863,
       "step": 318
     },
     {
       "epoch": 2.0,
-      "grad_norm": 3.8856751918792725,
+      "grad_norm": 4.324426651000977,
       "learning_rate": 6.6876310272536696e-06,
-      "loss": 1.1765,
+      "loss": 1.1524,
       "step": 636
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9412903225806452,
-      "eval_f1": 0.9402146858730125,
-      "eval_loss": 1.036224126815796,
-      "eval_model_preparation_time": 0.0029,
-      "eval_runtime": 17.3187,
-      "eval_samples_per_second": 178.997,
-      "eval_steps_per_second": 3.753,
+      "eval_accuracy": 0.94,
+      "eval_f1": 0.9386540826458253,
+      "eval_loss": 1.0111862421035767,
+      "eval_runtime": 16.5402,
+      "eval_samples_per_second": 187.422,
+      "eval_steps_per_second": 3.93,
       "step": 636
     }
   ],
@@ -76,8 +74,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.4894773949849175,
+    "alpha": 0.5616085539831922,
     "num_train_epochs": 3,
-    "temperature": 20
+    "temperature": 14
   }
 }

run-2/checkpoint-636/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7b3769acf391cea03ef15fd35cf3a1a8ad375b715605c557f3506a2acf1661
+oid sha256:ac0ba789da4d8d3fec25ab5f556d37cdc9662d151e6cf3587f40da34600391df
 size 5905

runs/Oct11_19-55-54_cd07aeb3aeb4/events.out.tfevents.1760215466.cd07aeb3aeb4.2948.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85145d834b697b1bed0f4173a589361272285753515c031a2627b376ccd44b2c
-size 13790
+oid sha256:57c2daa5b8175b293830d0200cf907aedd89aa33ed4e69310d8d97d7fc73923d
+size 14370