Training in progress, epoch 16

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20240924_172630-x9iddikd/run-x9iddikd.wandb filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0505695cf303da48c7fdc01b3e844c17229610edb63ad1c8b203405e2fd9c2e
+oid sha256:19458ef42771c182153262f655bd6b33bc0819768cf3595ef5483008c6217ef1
 size 267832560

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

@@ -47,3 +47,6 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'loss': 0.0442, 'grad_norm': 0.6364777684211731, 'learning_rate': 7.600000000000001e-06, 'epoch': 12.0}
 {'eval_loss': 0.578902006149292, 'eval_accuracy': 0.903, 'eval_runtime': 38.2969, 'eval_samples_per_second': 26.112, 'eval_steps_per_second': 0.836, 'epoch': 12.0}
 {'eval_loss': 0.47741687297821045, 'eval_accuracy': 0.92, 'eval_runtime': 37.7268, 'eval_samples_per_second': 26.506, 'eval_steps_per_second': 0.848, 'epoch': 13.0}
+{'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}

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

@@ -1 +1 @@
-{"eval/loss": 0.5484298467636108, "eval/accuracy": 0.894, "eval/runtime": 38.013, "eval/samples_per_second": 26.307, "eval/steps_per_second": 0.842, "train/epoch": 14.0, "train/global_step": 1750, "_timestamp": 1727244298.3548748, "_runtime": 34707.48196578026, "_step": 24, "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}
+{"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}