Training in progress, epoch 23

log.txt

@@ -165,3 +165,11 @@
 {'loss': 0.0575, 'grad_norm': 9.76453971862793, 'learning_rate': 2.847392369618481e-05, 'epoch': 21.53}
 {'loss': 0.061, 'grad_norm': 4.032108783721924, 'learning_rate': 2.829891494574729e-05, 'epoch': 21.7}
 {'loss': 0.061, 'grad_norm': 6.91244649887085, 'learning_rate': 2.812390619530977e-05, 'epoch': 21.88}
+[3 3 1 ... 3 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 4.351003170013428, 'eval_accuracy': 0.4066459478842936, 'eval_runtime': 5.1312, 'eval_samples_per_second': 815.21, 'eval_steps_per_second': 12.863, 'epoch': 22.0}
+{'loss': 0.0585, 'grad_norm': 6.355452060699463, 'learning_rate': 2.7948897444872246e-05, 'epoch': 22.05}
+{'loss': 0.0533, 'grad_norm': 3.642059803009033, 'learning_rate': 2.7773888694434723e-05, 'epoch': 22.23}
+{'loss': 0.0553, 'grad_norm': 10.472013473510742, 'learning_rate': 2.7598879943997203e-05, 'epoch': 22.4}
+{'loss': 0.0544, 'grad_norm': 6.09908390045166, 'learning_rate': 2.742387119355968e-05, 'epoch': 22.58}
+{'loss': 0.0572, 'grad_norm': 7.71782112121582, 'learning_rate': 2.7248862443122158e-05, 'epoch': 22.75}
+{'loss': 0.0599, 'grad_norm': 6.481327533721924, 'learning_rate': 2.7073853692684635e-05, 'epoch': 22.93}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3461102181cd846d2a168682c810e95aa1a95bd65f1af2f7904a999778fb675a
+oid sha256:7c1c7c7465e63cd28c09a42539b63cf5052e067a41e1c00b4efa082ac78cfbf7
 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:f556dc32bb12b335282f34d34d4c8f83dea8330570031b9ce4b92fdfb47c258d
-size 38630
+oid sha256:abfefde7ca0769ec0d411d53f2c8be8354833928f5bb922f211bdcdc8379ba8e
+size 40249