Training in progress, epoch 3

log.txt

@@ -11,3 +11,11 @@
 {'loss': 1.1927, 'grad_norm': 4.891911029815674, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
 {'loss': 1.1693, 'grad_norm': 4.698267936706543, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
 {'loss': 1.1604, 'grad_norm': 5.036068439483643, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
+[3 3 3 ... 0 0 1] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.4321914911270142, 'eval_accuracy': 0.349270858235716, 'eval_runtime': 9.2733, 'eval_samples_per_second': 451.081, 'eval_steps_per_second': 7.117, 'epoch': 2.0}
+{'loss': 1.067, 'grad_norm': 8.549752235412598, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
+{'loss': 0.9953, 'grad_norm': 8.00672721862793, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
+{'loss': 0.9925, 'grad_norm': 8.322041511535645, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
+{'loss': 0.9878, 'grad_norm': 7.179974555969238, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
+{'loss': 0.9789, 'grad_norm': 7.508288860321045, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
+{'loss': 0.9724, 'grad_norm': 7.802349090576172, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a49d430a6691e81a93ae0aef9644ea1470c77e67c102ef7ef8551bb414627f3
+oid sha256:6400ebdb66cc13d3a088adcaf43706fb21167d1a28eb2a21a15b91f3237c948e
 size 437961884

runs/Mar12_19-30-48_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710297050.cehsc-app-001.ad.unlv.edu.2573046.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3e85521807c3784a89356ae3856d0f83481e733c0eec3745c3fe460c0bcbc3
-size 7614
+oid sha256:19b4149d8a2634450c9d5e447417092640e3c8010009b03c0ba224ee30949f99
+size 9557