Training in progress, epoch 3
Browse files
log.txt
CHANGED
@@ -22,3 +22,17 @@
|
|
22 |
{'loss': 1.1503, 'grad_norm': 4.793179035186768, 'learning_rate': 4.416637498541594e-05, 'epoch': 1.75}
|
23 |
{'loss': 1.1562, 'grad_norm': 5.454382419586182, 'learning_rate': 4.3874693734686735e-05, 'epoch': 1.84}
|
24 |
{'loss': 1.1366, 'grad_norm': 4.958292484283447, 'learning_rate': 4.358301248395754e-05, 'epoch': 1.93}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
{'loss': 1.1503, 'grad_norm': 4.793179035186768, 'learning_rate': 4.416637498541594e-05, 'epoch': 1.75}
|
23 |
{'loss': 1.1562, 'grad_norm': 5.454382419586182, 'learning_rate': 4.3874693734686735e-05, 'epoch': 1.84}
|
24 |
{'loss': 1.1366, 'grad_norm': 4.958292484283447, 'learning_rate': 4.358301248395754e-05, 'epoch': 1.93}
|
25 |
+
[0 0 3 ... 1 2 0] [0 0 2 ... 0 1 0]
|
26 |
+
{'eval_loss': 1.3753255605697632, 'eval_accuracy': 0.36337556777432467, 'eval_runtime': 6.416, 'eval_samples_per_second': 651.964, 'eval_steps_per_second': 20.418, 'epoch': 2.0}
|
27 |
+
{'loss': 1.0888, 'grad_norm': 7.227815628051758, 'learning_rate': 4.3291331233228335e-05, 'epoch': 2.01}
|
28 |
+
{'loss': 0.92, 'grad_norm': 7.727498531341553, 'learning_rate': 4.299964998249913e-05, 'epoch': 2.1}
|
29 |
+
{'loss': 0.9166, 'grad_norm': 6.4145636558532715, 'learning_rate': 4.270796873176993e-05, 'epoch': 2.19}
|
30 |
+
{'loss': 0.9126, 'grad_norm': 7.5823974609375, 'learning_rate': 4.2416287481040724e-05, 'epoch': 2.28}
|
31 |
+
{'loss': 0.9083, 'grad_norm': 7.961126327514648, 'learning_rate': 4.212460623031152e-05, 'epoch': 2.36}
|
32 |
+
{'loss': 0.928, 'grad_norm': 9.727679252624512, 'learning_rate': 4.183292497958232e-05, 'epoch': 2.45}
|
33 |
+
{'loss': 0.9128, 'grad_norm': 6.986959934234619, 'learning_rate': 4.1541243728853114e-05, 'epoch': 2.54}
|
34 |
+
{'loss': 0.9124, 'grad_norm': 11.424525260925293, 'learning_rate': 4.124956247812391e-05, 'epoch': 2.63}
|
35 |
+
{'loss': 0.9054, 'grad_norm': 7.206017971038818, 'learning_rate': 4.0957881227394707e-05, 'epoch': 2.71}
|
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}
|
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:ec267016e3c76de1b6a58414d5af4063f500f6cc56e4f8eb7669a0ce9e14299d
|
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 sha256:5032a94d1412e1b7641854104f5c5e58fd3bcb050e2c8a148030351842d95338
|
3 |
+
size 12724
|