Training in progress, epoch 17

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19458ef42771c182153262f655bd6b33bc0819768cf3595ef5483008c6217ef1
+oid sha256:e399ab6abc4060a7a5c82bf61bd64243ee82179bcbe87dbb15eb5046f0879a6d
 size 267832560

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

@@ -50,3 +50,4 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'eval_loss': 0.5484298467636108, 'eval_accuracy': 0.894, 'eval_runtime': 38.013, 'eval_samples_per_second': 26.307, 'eval_steps_per_second': 0.842, 'epoch': 14.0}
 {'eval_loss': 0.538878321647644, 'eval_accuracy': 0.909, 'eval_runtime': 38.0368, 'eval_samples_per_second': 26.29, 'eval_steps_per_second': 0.841, 'epoch': 15.0}
 {'loss': 0.0268, 'grad_norm': 20.58578109741211, 'learning_rate': 6.800000000000001e-06, 'epoch': 16.0}
+{'eval_loss': 0.49775975942611694, 'eval_accuracy': 0.921, 'eval_runtime': 37.3442, 'eval_samples_per_second': 26.778, 'eval_steps_per_second': 0.857, 'epoch': 16.0}

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

@@ -1 +1 @@
-{"eval/loss": 0.49775975942611694, "eval/accuracy": 0.921, "eval/runtime": 37.3442, "eval/samples_per_second": 26.778, "eval/steps_per_second": 0.857, "train/epoch": 16.0, "train/global_step": 2000, "_timestamp": 1727247708.6516852, "_runtime": 38117.77877616882, "_step": 27, "train/loss": 0.0268, "train/grad_norm": 20.58578109741211, "train/learning_rate": 6.800000000000001e-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": 0.5782524347305298, "eval/accuracy": 0.909, "eval/runtime": 38.4136, "eval/samples_per_second": 26.032, "eval/steps_per_second": 0.833, "train/epoch": 17.0, "train/global_step": 2125, "_timestamp": 1727249410.148884, "_runtime": 39819.27597498894, "_step": 28, "train/loss": 0.0268, "train/grad_norm": 20.58578109741211, "train/learning_rate": 6.800000000000001e-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}

wandb/run-20240924_172630-x9iddikd/run-x9iddikd.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b15437c0304530f580ce3e932b8263c57a737a167c1c3db4c242c42db50cddd
-size 1049292
+oid sha256:581b3245072ad2dd943a8822cb113c5812c85973b4d1b1f68686b5b3e54d9240
+size 1094007