Training in progress, epoch 12

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49146c9cd541b88129d9ea09ad2c3a4b9a7a2ac95d7582414a1f4a01d681f002
+oid sha256:4037e7c12241893a0f8b913615756f39907cef7d40a35227116403d19ba58f35
 size 267832560

wandb/run-20240924_172630-x9iddikd/files/output.log

@@ -43,3 +43,5 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'eval_loss': 0.4580109715461731, 'eval_accuracy': 0.91, 'eval_runtime': 38.2702, 'eval_samples_per_second': 26.13, 'eval_steps_per_second': 0.836, 'epoch': 8.0}
 {'eval_loss': 0.4977562129497528, 'eval_accuracy': 0.913, 'eval_runtime': 37.7002, 'eval_samples_per_second': 26.525, 'eval_steps_per_second': 0.849, 'epoch': 9.0}
 {'eval_loss': 0.4662289023399353, 'eval_accuracy': 0.92, 'eval_runtime': 38.4422, 'eval_samples_per_second': 26.013, 'eval_steps_per_second': 0.832, 'epoch': 10.0}
+{'eval_loss': 0.5506279468536377, 'eval_accuracy': 0.901, 'eval_runtime': 37.4907, 'eval_samples_per_second': 26.673, 'eval_steps_per_second': 0.854, 'epoch': 11.0}
+{'loss': 0.0442, 'grad_norm': 0.6364777684211731, 'learning_rate': 7.600000000000001e-06, 'epoch': 12.0}

wandb/run-20240924_172630-x9iddikd/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 0.5506279468536377, "eval/accuracy": 0.901, "eval/runtime": 37.4907, "eval/samples_per_second": 26.673, "eval/steps_per_second": 0.854, "train/epoch": 11.0, "train/global_step": 1375, "_timestamp": 1727239149.997223, "_runtime": 29559.12431383133, "_step": 20, "train/loss": 0.1013, "train/grad_norm": 0.6478258371353149, "train/learning_rate": 8.400000000000001e-06, "train_runtime": 8026.8642, "train_samples_per_second": 2.492, "train_steps_per_second": 0.156, "total_flos": 2396475988298112.0, "train_loss": 0.11480112991333008}
+{"eval/loss": 0.578902006149292, "eval/accuracy": 0.903, "eval/runtime": 38.2969, "eval/samples_per_second": 26.112, "eval/steps_per_second": 0.836, "train/epoch": 12.0, "train/global_step": 1500, "_timestamp": 1727240843.341215, "_runtime": 31252.468305826187, "_step": 22, "train/loss": 0.0442, "train/grad_norm": 0.6364777684211731, "train/learning_rate": 7.600000000000001e-06, "train_runtime": 8026.8642, "train_samples_per_second": 2.492, "train_steps_per_second": 0.156, "total_flos": 2396475988298112.0, "train_loss": 0.11480112991333008}