Training in progress, epoch 3

log.txt

@@ -11,3 +11,11 @@
 {'loss': 1.3874, 'grad_norm': 0.5867350697517395, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
 {'loss': 1.3878, 'grad_norm': 0.516469419002533, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
 {'loss': 1.3871, 'grad_norm': 0.4514859616756439, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
+[2 0 3 ... 0 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.3862946033477783, 'eval_accuracy': 0.22973942146784604, 'eval_runtime': 12.7723, 'eval_samples_per_second': 327.505, 'eval_steps_per_second': 5.167, 'epoch': 2.0}
+{'loss': 1.3874, 'grad_norm': 0.6036933064460754, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
+{'loss': 1.3876, 'grad_norm': 0.5512823462486267, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
+{'loss': 1.3872, 'grad_norm': 0.556095540523529, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
+{'loss': 1.3869, 'grad_norm': 0.47949934005737305, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
+{'loss': 1.3871, 'grad_norm': 0.45945364236831665, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
+{'loss': 1.3869, 'grad_norm': 0.48113781213760376, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7caedc459dead377136c0ab4f7f242b20e687ca3f12417c0c9f9bd9ede4e4d7a
+oid sha256:fe02015cf32bdf94cc17eb611826ee41b1b68ce90169356095208eb276edb699
 size 1112201908

runs/Mar13_08-54-43_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710345286.cehsc-app-001.ad.unlv.edu.2936732.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c19aa7e95db1f59fe2b8ae0c48fa9f751207ba3e4091d57ef0ec636ecdf8804
-size 7648
+oid sha256:3937c13f3e01377c50e9d7b2291e724eb2a56a10bf4287bbf09cec1c8c3b2d64
+size 9591