Training in progress, epoch 2
Browse files
log.txt
CHANGED
@@ -9,3 +9,16 @@
|
|
9 |
{'loss': 1.3195, 'grad_norm': 1.9234343767166138, 'learning_rate': 4.737486874343717e-05, 'epoch': 0.79}
|
10 |
{'loss': 1.3105, 'grad_norm': 2.1175739765167236, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.88}
|
11 |
{'loss': 1.2998, 'grad_norm': 2.521505117416382, 'learning_rate': 4.6791506241978764e-05, 'epoch': 0.96}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
{'loss': 1.3195, 'grad_norm': 1.9234343767166138, 'learning_rate': 4.737486874343717e-05, 'epoch': 0.79}
|
10 |
{'loss': 1.3105, 'grad_norm': 2.1175739765167236, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.88}
|
11 |
{'loss': 1.2998, 'grad_norm': 2.521505117416382, 'learning_rate': 4.6791506241978764e-05, 'epoch': 0.96}
|
12 |
+
[0 3 2 ... 1 0 2] [0 0 2 ... 0 1 0]
|
13 |
+
{'eval_loss': 1.3409068584442139, 'eval_accuracy': 0.34185990915610803, 'eval_runtime': 6.4784, 'eval_samples_per_second': 645.688, 'eval_steps_per_second': 20.221, 'epoch': 1.0}
|
14 |
+
{'loss': 1.2528, 'grad_norm': 4.092164039611816, 'learning_rate': 4.649982499124956e-05, 'epoch': 1.05}
|
15 |
+
{'loss': 1.1967, 'grad_norm': 6.143226623535156, 'learning_rate': 4.6208143740520357e-05, 'epoch': 1.14}
|
16 |
+
{'loss': 1.1974, 'grad_norm': 4.76519250869751, 'learning_rate': 4.591646248979116e-05, 'epoch': 1.23}
|
17 |
+
{'loss': 1.1884, 'grad_norm': 5.0817179679870605, 'learning_rate': 4.5624781239061956e-05, 'epoch': 1.31}
|
18 |
+
{'loss': 1.182, 'grad_norm': 4.871830463409424, 'learning_rate': 4.533309998833275e-05, 'epoch': 1.4}
|
19 |
+
{'loss': 1.1814, 'grad_norm': 5.66860818862915, 'learning_rate': 4.504141873760355e-05, 'epoch': 1.49}
|
20 |
+
{'loss': 1.1712, 'grad_norm': 5.154982089996338, 'learning_rate': 4.4749737486874346e-05, 'epoch': 1.58}
|
21 |
+
{'loss': 1.1556, 'grad_norm': 6.135748863220215, 'learning_rate': 4.445805623614514e-05, 'epoch': 1.66}
|
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}
|
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 sha256:0c48296919c05850f8690e8fede7f02c714263219b9e172003051dc629bbcb74
|
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 sha256:2e8317f15b160eea7b125991331f8f6868702919309fd9b9d187963b99f99b2d
|
3 |
+
size 9855
|