Training in progress, epoch 3

log.txt

@@ -11,3 +11,11 @@
 {'loss': 1.387, 'grad_norm': 0.3263598084449768, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
 {'loss': 1.387, 'grad_norm': 0.49747857451438904, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
 {'loss': 1.3869, 'grad_norm': 0.42442792654037476, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
+[0 1 2 ... 3 3 2] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.3862944841384888, 'eval_accuracy': 0.2816160650251016, 'eval_runtime': 8.68, 'eval_samples_per_second': 481.91, 'eval_steps_per_second': 7.604, 'epoch': 2.0}
+{'loss': 1.387, 'grad_norm': 0.3492703139781952, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
+{'loss': 1.3871, 'grad_norm': 0.41146495938301086, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
+{'loss': 1.387, 'grad_norm': 0.43965476751327515, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
+{'loss': 1.3866, 'grad_norm': 0.28787338733673096, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
+{'loss': 1.3867, 'grad_norm': 0.36737778782844543, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
+{'loss': 1.3868, 'grad_norm': 0.3487311601638794, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d44da5efa316a552b960e1feb49bc0aa8d7748e4139ec1adb40bf4811998ca
+oid sha256:775a26da3af2fe876c514f753d205c88d3dd0177a46239927bb7c36898b77317
 size 498609724

runs/Mar13_03-36-49_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710326212.cehsc-app-001.ad.unlv.edu.2829537.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5160f6e5155ca28f17823aa2acf0a525ada3e52ab7b3dbd2c9d439a1186e6c
-size 7601
+oid sha256:08448fd9e684a2074c631f6ee03e9f071954fe566e20253650bef45c3b8a829d
+size 9544