Training in progress, epoch 15
Browse files
log.txt
CHANGED
@@ -183,3 +183,17 @@
|
|
183 |
{'loss': 0.0704, 'grad_norm': 6.768477916717529, 'learning_rate': 4.206043635515109e-06, 'epoch': 13.74}
|
184 |
{'loss': 0.0711, 'grad_norm': 10.230005264282227, 'learning_rate': 3.914362384785906e-06, 'epoch': 13.83}
|
185 |
{'loss': 0.0823, 'grad_norm': 0.6493052244186401, 'learning_rate': 3.6226811340567034e-06, 'epoch': 13.91}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
{'loss': 0.0704, 'grad_norm': 6.768477916717529, 'learning_rate': 4.206043635515109e-06, 'epoch': 13.74}
|
184 |
{'loss': 0.0711, 'grad_norm': 10.230005264282227, 'learning_rate': 3.914362384785906e-06, 'epoch': 13.83}
|
185 |
{'loss': 0.0823, 'grad_norm': 0.6493052244186401, 'learning_rate': 3.6226811340567034e-06, 'epoch': 13.91}
|
186 |
+
[0 2 2 ... 0 2 0] [0 0 2 ... 0 1 0]
|
187 |
+
{'eval_loss': 6.0199151039123535, 'eval_accuracy': 0.4159693999521874, 'eval_runtime': 6.215, 'eval_samples_per_second': 673.045, 'eval_steps_per_second': 21.078, 'epoch': 14.0}
|
188 |
+
{'loss': 0.0716, 'grad_norm': 12.979365348815918, 'learning_rate': 3.3309998833275e-06, 'epoch': 14.0}
|
189 |
+
{'loss': 0.0664, 'grad_norm': 6.599959850311279, 'learning_rate': 3.0393186325982967e-06, 'epoch': 14.09}
|
190 |
+
{'loss': 0.0683, 'grad_norm': 8.023162841796875, 'learning_rate': 2.7476373818690932e-06, 'epoch': 14.18}
|
191 |
+
{'loss': 0.0608, 'grad_norm': 16.25693702697754, 'learning_rate': 2.4559561311398905e-06, 'epoch': 14.26}
|
192 |
+
{'loss': 0.0694, 'grad_norm': 0.4397706985473633, 'learning_rate': 2.1642748804106874e-06, 'epoch': 14.35}
|
193 |
+
{'loss': 0.0708, 'grad_norm': 0.14326095581054688, 'learning_rate': 1.8725936296814843e-06, 'epoch': 14.44}
|
194 |
+
{'loss': 0.0586, 'grad_norm': 10.660558700561523, 'learning_rate': 1.580912378952281e-06, 'epoch': 14.53}
|
195 |
+
{'loss': 0.0661, 'grad_norm': 23.552616119384766, 'learning_rate': 1.289231128223078e-06, 'epoch': 14.61}
|
196 |
+
{'loss': 0.0723, 'grad_norm': 0.8439858555793762, 'learning_rate': 9.975498774938746e-07, 'epoch': 14.7}
|
197 |
+
{'loss': 0.061, 'grad_norm': 8.804609298706055, 'learning_rate': 7.058686267646716e-07, 'epoch': 14.79}
|
198 |
+
{'loss': 0.0618, 'grad_norm': 29.952268600463867, 'learning_rate': 4.141873760354685e-07, 'epoch': 14.88}
|
199 |
+
{'loss': 0.0631, 'grad_norm': 0.013782646507024765, 'learning_rate': 1.225061253062653e-07, 'epoch': 14.96}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c92f168fcd8c7aaf11652fbc0dfdc82d2bc089bb00bb69fcac912782225f341
|
3 |
size 267829484
|
runs/Mar14_16-58-52_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710460734.cehsc-app-001.ad.unlv.edu.4089564.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a2cafdd802f72b1b344d91eb479468f8a84d6788744524e223ccec74e546830
|
3 |
+
size 46487
|