Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8934bd46cb1d211e89a648589db21b00b2653c8a5559c6f8554ead0dd889558e
+oid sha256:80d16899c96c3df71080ce0e7df58e2205dcfcf86c4e8331937636a0d9789723
 size 267832560

wandb/run-20240923_004152-7jibscvo/files/output.log

@@ -10,3 +10,8 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'loss': 0.1689, 'grad_norm': 7.930511474609375, 'learning_rate': 1.488163787587972e-05, 'epoch': 1.28}
 {'loss': 0.1504, 'grad_norm': 36.72976303100586, 'learning_rate': 1.3602047344849649e-05, 'epoch': 1.6}
 {'loss': 0.1526, 'grad_norm': 0.9081774353981018, 'learning_rate': 1.2322456813819578e-05, 'epoch': 1.92}
+{'eval_loss': 0.2298162430524826, 'eval_accuracy': 0.92924, 'eval_runtime': 898.8856, 'eval_samples_per_second': 27.812, 'eval_steps_per_second': 1.739, 'epoch': 2.0}
+{'loss': 0.1017, 'grad_norm': 0.0514792837202549, 'learning_rate': 1.1042866282789508e-05, 'epoch': 2.24}
+{'loss': 0.08, 'grad_norm': 0.046891484409570694, 'learning_rate': 9.763275751759437e-06, 'epoch': 2.56}
+{'loss': 0.0893, 'grad_norm': 0.06083718314766884, 'learning_rate': 8.483685220729368e-06, 'epoch': 2.88}
+wandb: ERROR Error while calling W&B API: context deadline exceeded (<Response [500]>)

wandb/run-20240923_004152-7jibscvo/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.1526, "train/grad_norm": 0.9081774353981018, "train/learning_rate": 1.2322456813819578e-05, "train/epoch": 2.0, "train/global_step": 3126, "_timestamp": 1727085575.407219, "_runtime": 22663.289223909378, "_step": 7, "eval/loss": 0.2298162430524826, "eval/accuracy": 0.92924, "eval/runtime": 898.8856, "eval/samples_per_second": 27.812, "eval/steps_per_second": 1.739}
+{"train/loss": 0.0893, "train/grad_norm": 0.06083718314766884, "train/learning_rate": 8.483685220729368e-06, "train/epoch": 3.0, "train/global_step": 4689, "_timestamp": 1727098789.535688, "_runtime": 35877.417692899704, "_step": 11, "eval/loss": 0.2804093658924103, "eval/accuracy": 0.93296, "eval/runtime": 1235.9411, "eval/samples_per_second": 20.228, "eval/steps_per_second": 1.265}