Training in progress, epoch 12

log.txt

@@ -80,3 +80,11 @@
 {'loss': 0.1605, 'grad_norm': 11.409436225891113, 'learning_rate': 3.949947497374869e-05, 'epoch': 10.5}
 {'loss': 0.1671, 'grad_norm': 9.97114372253418, 'learning_rate': 3.932446622331117e-05, 'epoch': 10.68}
 {'loss': 0.1697, 'grad_norm': 8.829890251159668, 'learning_rate': 3.914945747287364e-05, 'epoch': 10.85}
+[1 2 3 ... 0 1 0] [0 0 2 ... 0 1 0]
+{'eval_loss': 3.009945869445801, 'eval_accuracy': 0.39875687305761415, 'eval_runtime': 5.0345, 'eval_samples_per_second': 830.865, 'eval_steps_per_second': 13.11, 'epoch': 11.0}
+{'loss': 0.165, 'grad_norm': 5.728878974914551, 'learning_rate': 3.8974448722436124e-05, 'epoch': 11.03}
+{'loss': 0.1222, 'grad_norm': 8.60106086730957, 'learning_rate': 3.8799439971998605e-05, 'epoch': 11.2}
+{'loss': 0.1342, 'grad_norm': 7.297552108764648, 'learning_rate': 3.862443122156108e-05, 'epoch': 11.38}
+{'loss': 0.1353, 'grad_norm': 4.835112571716309, 'learning_rate': 3.844942247112356e-05, 'epoch': 11.55}
+{'loss': 0.1392, 'grad_norm': 11.95632553100586, 'learning_rate': 3.827441372068604e-05, 'epoch': 11.73}
+{'loss': 0.1528, 'grad_norm': 10.495340347290039, 'learning_rate': 3.809940497024851e-05, 'epoch': 11.9}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f615c4a14e0acf6b9df7c67ae3675d677ce4e673ccf7c5902675d55bd205e6a
+oid sha256:c0ad5c646b1ab0b1f8777cedc844577b8c1ee42b199bed3571a3cf9418c6bf24
 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:ee47816a4543d639d4002b1581c3d99325cfdf4fc4cede2704d4fd3b90718ee6
-size 21466
+oid sha256:bcd735ab26f8342374c7697a2d6cae19c7e0fd050d526f5ddac3513f16858efb
+size 23085