Training in progress, epoch 5

log.txt

@@ -26,3 +26,11 @@
 {'loss': 0.6865, 'grad_norm': 7.7962565422058105, 'learning_rate': 4.649982499124956e-05, 'epoch': 3.5}
 {'loss': 0.6819, 'grad_norm': 7.269796848297119, 'learning_rate': 4.632481624081204e-05, 'epoch': 3.68}
 {'loss': 0.696, 'grad_norm': 8.324944496154785, 'learning_rate': 4.614980749037452e-05, 'epoch': 3.85}
+[3 3 2 ... 0 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.6681735515594482, 'eval_accuracy': 0.396127181448721, 'eval_runtime': 5.0295, 'eval_samples_per_second': 831.699, 'eval_steps_per_second': 13.123, 'epoch': 4.0}
+{'loss': 0.667, 'grad_norm': 10.500767707824707, 'learning_rate': 4.5974798739936995e-05, 'epoch': 4.03}
+{'loss': 0.4947, 'grad_norm': 10.41182804107666, 'learning_rate': 4.5799789989499476e-05, 'epoch': 4.2}
+{'loss': 0.5094, 'grad_norm': 10.82896614074707, 'learning_rate': 4.5624781239061956e-05, 'epoch': 4.38}
+{'loss': 0.5182, 'grad_norm': 7.591678619384766, 'learning_rate': 4.544977248862443e-05, 'epoch': 4.55}
+{'loss': 0.5407, 'grad_norm': 7.200017929077148, 'learning_rate': 4.527476373818691e-05, 'epoch': 4.73}
+{'loss': 0.5363, 'grad_norm': 9.024789810180664, 'learning_rate': 4.5099754987749384e-05, 'epoch': 4.9}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ce1437752bbd9ccf51f006d49ee0fa6a06e24edbfd9a033d6522424aacc241
+oid sha256:20fd30791c9b9548905cc037689e2ac6e6cce7cd4832cff65a5596ca3179d84f
 size 267829484

runs/Mar13_17-26-31_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710375994.cehsc-app-001.ad.unlv.edu.3270813.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b55d34e29e57a0ab3dc3ae28e72913b5a55d55871f7ba840dbc966a1454d1b
-size 10609
+oid sha256:2173ce60b41c8ee39558d8a44a0888bfff0a967638060fbd7f97910807c21bd9
+size 12198