Training in progress, epoch 3

log.txt

@@ -11,3 +11,11 @@
 {'loss': 1.3865, 'grad_norm': 0.13234885036945343, 'learning_rate': 2.374868743437172e-05, 'epoch': 1.58}
 {'loss': 1.3865, 'grad_norm': 0.11721161007881165, 'learning_rate': 2.083187492707969e-05, 'epoch': 1.75}
 {'loss': 1.3865, 'grad_norm': 0.1150147020816803, 'learning_rate': 1.7915062419787655e-05, 'epoch': 1.93}
+[3 2 2 ... 3 2 2] [0 0 2 ... 0 1 0]
+{'eval_loss': 1.3862881660461426, 'eval_accuracy': 0.26751135548649296, 'eval_runtime': 9.1114, 'eval_samples_per_second': 459.098, 'eval_steps_per_second': 7.244, 'epoch': 2.0}
+{'loss': 1.3864, 'grad_norm': 0.10965009778738022, 'learning_rate': 1.4998249912495627e-05, 'epoch': 2.1}
+{'loss': 1.3865, 'grad_norm': 0.11624345183372498, 'learning_rate': 1.2081437405203595e-05, 'epoch': 2.28}
+{'loss': 1.3863, 'grad_norm': 0.15024864673614502, 'learning_rate': 9.164624897911563e-06, 'epoch': 2.45}
+{'loss': 1.3863, 'grad_norm': 0.21923650801181793, 'learning_rate': 6.247812390619531e-06, 'epoch': 2.63}
+{'loss': 1.3863, 'grad_norm': 0.23588676750659943, 'learning_rate': 3.3309998833275e-06, 'epoch': 2.8}
+{'loss': 1.3868, 'grad_norm': 0.22491014003753662, 'learning_rate': 4.141873760354685e-07, 'epoch': 2.98}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7e9a4cb9cffad99a63af0ca93057fbee9bea035710580c991d15ffeb2a044d
+oid sha256:f3d3fc2356f8fd15743d9f48728fbc5a0c2f1eeda14323c5ef94538819132f0f
 size 437956148

runs/Mar12_18-34-29_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710293672.cehsc-app-001.ad.unlv.edu.2537628.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390a620c4fb4654dbb6477c0fa7db6a1fec9b9a771a2866b4e9cd3131798a2e1
-size 7745
+oid sha256:3212a11778c999fe09a10b1d101f8e52033633eee3e7e3b603695e48fb008c1a
+size 9688