Training in progress, epoch 4
Browse files
log.txt
CHANGED
@@ -36,3 +36,16 @@
|
|
36 |
{'loss': 0.8958, 'grad_norm': 6.930673122406006, 'learning_rate': 4.06661999766655e-05, 'epoch': 2.8}
|
37 |
{'loss': 0.9066, 'grad_norm': 7.441983222961426, 'learning_rate': 4.03745187259363e-05, 'epoch': 2.89}
|
38 |
{'loss': 0.9035, 'grad_norm': 8.201363563537598, 'learning_rate': 4.0082837475207096e-05, 'epoch': 2.98}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
{'loss': 0.8958, 'grad_norm': 6.930673122406006, 'learning_rate': 4.06661999766655e-05, 'epoch': 2.8}
|
37 |
{'loss': 0.9066, 'grad_norm': 7.441983222961426, 'learning_rate': 4.03745187259363e-05, 'epoch': 2.89}
|
38 |
{'loss': 0.9035, 'grad_norm': 8.201363563537598, 'learning_rate': 4.0082837475207096e-05, 'epoch': 2.98}
|
39 |
+
[2 2 2 ... 2 2 0] [0 0 2 ... 0 1 0]
|
40 |
+
{'eval_loss': 1.4999252557754517, 'eval_accuracy': 0.3793927803012192, 'eval_runtime': 6.454, 'eval_samples_per_second': 648.13, 'eval_steps_per_second': 20.298, 'epoch': 3.0}
|
41 |
+
{'loss': 0.7189, 'grad_norm': 11.725881576538086, 'learning_rate': 3.979115622447789e-05, 'epoch': 3.06}
|
42 |
+
{'loss': 0.6632, 'grad_norm': 13.215302467346191, 'learning_rate': 3.949947497374869e-05, 'epoch': 3.15}
|
43 |
+
{'loss': 0.6687, 'grad_norm': 10.268899917602539, 'learning_rate': 3.9207793723019485e-05, 'epoch': 3.24}
|
44 |
+
{'loss': 0.667, 'grad_norm': 8.265130043029785, 'learning_rate': 3.891611247229028e-05, 'epoch': 3.33}
|
45 |
+
{'loss': 0.6665, 'grad_norm': 12.575718879699707, 'learning_rate': 3.862443122156108e-05, 'epoch': 3.41}
|
46 |
+
{'loss': 0.6859, 'grad_norm': 14.319367408752441, 'learning_rate': 3.8332749970831875e-05, 'epoch': 3.5}
|
47 |
+
{'loss': 0.6866, 'grad_norm': 11.042840957641602, 'learning_rate': 3.804106872010267e-05, 'epoch': 3.59}
|
48 |
+
{'loss': 0.6859, 'grad_norm': 12.115802764892578, 'learning_rate': 3.774938746937347e-05, 'epoch': 3.68}
|
49 |
+
{'loss': 0.6788, 'grad_norm': 9.712413787841797, 'learning_rate': 3.7457706218644264e-05, 'epoch': 3.76}
|
50 |
+
{'loss': 0.6904, 'grad_norm': 9.902729034423828, 'learning_rate': 3.716602496791506e-05, 'epoch': 3.85}
|
51 |
+
{'loss': 0.6883, 'grad_norm': 9.378089904785156, 'learning_rate': 3.6874343717185864e-05, 'epoch': 3.94}
|
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:f391f584ff52257b8c6984c51f7ad92ed55cd8fdee016769172c87a43c9ad077
|
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 sha256:96b86bd506b776ffb5f3ba6257339094ed30a117609acd1f1eda864a94d74095
|
3 |
+
size 15418
|