Training in progress, epoch 16

log.txt

@@ -111,3 +111,11 @@
 {'loss': 0.1014, 'grad_norm': 7.694157123565674, 'learning_rate': 3.547427371368569e-05, 'epoch': 14.53}
 {'loss': 0.1067, 'grad_norm': 12.248181343078613, 'learning_rate': 3.529926496324816e-05, 'epoch': 14.7}
 {'loss': 0.1086, 'grad_norm': 9.317180633544922, 'learning_rate': 3.512425621281064e-05, 'epoch': 14.88}
+[3 2 3 ... 3 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 3.6231369972229004, 'eval_accuracy': 0.4030600047812575, 'eval_runtime': 5.3002, 'eval_samples_per_second': 789.213, 'eval_steps_per_second': 12.452, 'epoch': 15.0}
+{'loss': 0.1006, 'grad_norm': 10.558964729309082, 'learning_rate': 3.494924746237312e-05, 'epoch': 15.05}
+{'loss': 0.0861, 'grad_norm': 10.458243370056152, 'learning_rate': 3.47742387119356e-05, 'epoch': 15.23}
+{'loss': 0.093, 'grad_norm': 9.602523803710938, 'learning_rate': 3.459922996149808e-05, 'epoch': 15.4}
+{'loss': 0.0933, 'grad_norm': 4.416888236999512, 'learning_rate': 3.442422121106055e-05, 'epoch': 15.58}
+{'loss': 0.0936, 'grad_norm': 10.379509925842285, 'learning_rate': 3.424921246062303e-05, 'epoch': 15.75}
+{'loss': 0.0946, 'grad_norm': 8.990747451782227, 'learning_rate': 3.4074203710185506e-05, 'epoch': 15.93}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965b37fcd950725e5870db79bbc8b5816a77c6ae063cf329d10b6fbd4144941b
+oid sha256:81a5c9e06f0c1710863607c0851f2e7194a5a93bf7003a7237d8c0c9d7c1d17a
 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 sha256:9531a2cbc98e84a8efe1d402601022fe6be445928b09081a18aedc3f0b8e7f94
-size 27727
+oid sha256:079eb562cb65ce8c583359b110c7f73fd25e6f475cd4c5b9bb9e07dd67add584
+size 29346