Training in progress, epoch 3

log.txt

@@ -11,3 +11,11 @@
 {'loss': 1.3365, 'grad_norm': 2.3026928901672363, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
 {'loss': 1.3277, 'grad_norm': 1.6010768413543701, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
 {'loss': 1.3233, 'grad_norm': 1.8152786493301392, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
+[0 0 3 ... 1 0 2] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.345216989517212, 'eval_accuracy': 0.3296677026057853, 'eval_runtime': 16.0379, 'eval_samples_per_second': 260.819, 'eval_steps_per_second': 4.115, 'epoch': 2.0}
+{'loss': 1.3059, 'grad_norm': 2.303391456604004, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
+{'loss': 1.2857, 'grad_norm': 2.5327250957489014, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
+{'loss': 1.2841, 'grad_norm': 2.771071434020996, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
+{'loss': 1.2811, 'grad_norm': 3.016386032104492, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
+{'loss': 1.2806, 'grad_norm': 2.3957359790802, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
+{'loss': 1.2776, 'grad_norm': 2.706343412399292, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0dac9c5fd33919abb4151851b2fcab281f653eacd5090d9179a1e07b8f8c526
+oid sha256:1c6fe50a71a50c6f236c94b63d5aff4d3973b24d57341b3e7bbf4d43aa422171
 size 98468060

runs/Mar12_23-46-21_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710312384.cehsc-app-001.ad.unlv.edu.2715464.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a34cd0266e764328c4a54c2dabda61065ac7fc755492917b33a3323c9e3a97
-size 7825
+oid sha256:b526bb36d008eacf425c6a5dee88f9ac6f8ca2e7f1c93d4c77b19b6fef8d0004
+size 9768