Training in progress, epoch 41

log.txt

@@ -304,3 +304,11 @@
 {'loss': 0.0208, 'grad_norm': 13.089346885681152, 'learning_rate': 1.0448022401120058e-05, 'epoch': 39.55}
 {'loss': 0.0191, 'grad_norm': 9.088654518127441, 'learning_rate': 1.0273013650682535e-05, 'epoch': 39.73}
 {'loss': 0.0185, 'grad_norm': 0.02565234899520874, 'learning_rate': 1.0098004900245014e-05, 'epoch': 39.9}
+[3 2 3 ... 3 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 7.876224994659424, 'eval_accuracy': 0.41549127420511595, 'eval_runtime': 4.8077, 'eval_samples_per_second': 870.067, 'eval_steps_per_second': 13.728, 'epoch': 40.0}
+{'loss': 0.0156, 'grad_norm': 0.03860479220747948, 'learning_rate': 9.922996149807491e-06, 'epoch': 40.08}
+{'loss': 0.0153, 'grad_norm': 0.3213302791118622, 'learning_rate': 9.74798739936997e-06, 'epoch': 40.25}
+{'loss': 0.0185, 'grad_norm': 9.212058067321777, 'learning_rate': 9.572978648932447e-06, 'epoch': 40.43}
+{'loss': 0.0168, 'grad_norm': 0.3707139790058136, 'learning_rate': 9.397969898494926e-06, 'epoch': 40.6}
+{'loss': 0.017, 'grad_norm': 0.32125115394592285, 'learning_rate': 9.222961148057403e-06, 'epoch': 40.78}
+{'loss': 0.0165, 'grad_norm': 0.12538419663906097, 'learning_rate': 9.047952397619882e-06, 'epoch': 40.95}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837370d8452ea6183c7858364eaf8d6dffe0af58b8c5c9d845e70dbdb9123dfb
+oid sha256:fa9cd02ed27c64df4077e8191ac4566d3b55d83b2a1d5025e655da29bad8b35e
 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:e8bf9e62c17fc2bdf7976372a84e842e66065bf102a9534eb495663d738fa807
-size 66697
+oid sha256:6f06b66429106c93f004d6ec1c7a03a4a987d4490f58c038f6bdafea1f30de71
+size 68316