Training in progress, epoch 8
Browse files
log.txt
CHANGED
@@ -89,3 +89,17 @@
|
|
89 |
{'loss': 0.2945, 'grad_norm': 10.245756149291992, 'learning_rate': 2.754054369385136e-05, 'epoch': 6.74}
|
90 |
{'loss': 0.2869, 'grad_norm': 12.929959297180176, 'learning_rate': 2.7248862443122158e-05, 'epoch': 6.83}
|
91 |
{'loss': 0.2936, 'grad_norm': 7.713830471038818, 'learning_rate': 2.6957181192392954e-05, 'epoch': 6.91}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
{'loss': 0.2945, 'grad_norm': 10.245756149291992, 'learning_rate': 2.754054369385136e-05, 'epoch': 6.74}
|
90 |
{'loss': 0.2869, 'grad_norm': 12.929959297180176, 'learning_rate': 2.7248862443122158e-05, 'epoch': 6.83}
|
91 |
{'loss': 0.2936, 'grad_norm': 7.713830471038818, 'learning_rate': 2.6957181192392954e-05, 'epoch': 6.91}
|
92 |
+
[0 2 2 ... 1 2 1] [0 0 2 ... 0 1 0]
|
93 |
+
{'eval_loss': 2.7999720573425293, 'eval_accuracy': 0.4121443939756156, 'eval_runtime': 6.3661, 'eval_samples_per_second': 657.07, 'eval_steps_per_second': 20.578, 'epoch': 7.0}
|
94 |
+
{'loss': 0.2878, 'grad_norm': 13.161710739135742, 'learning_rate': 2.666549994166375e-05, 'epoch': 7.0}
|
95 |
+
{'loss': 0.2004, 'grad_norm': 6.0921101570129395, 'learning_rate': 2.6373818690934547e-05, 'epoch': 7.09}
|
96 |
+
{'loss': 0.1963, 'grad_norm': 18.889543533325195, 'learning_rate': 2.6082137440205344e-05, 'epoch': 7.18}
|
97 |
+
{'loss': 0.2049, 'grad_norm': 20.18791961669922, 'learning_rate': 2.5790456189476144e-05, 'epoch': 7.26}
|
98 |
+
{'loss': 0.2065, 'grad_norm': 16.6495418548584, 'learning_rate': 2.549877493874694e-05, 'epoch': 7.35}
|
99 |
+
{'loss': 0.2239, 'grad_norm': 6.013281345367432, 'learning_rate': 2.5207093688017736e-05, 'epoch': 7.44}
|
100 |
+
{'loss': 0.2162, 'grad_norm': 13.363381385803223, 'learning_rate': 2.4915412437288533e-05, 'epoch': 7.53}
|
101 |
+
{'loss': 0.2227, 'grad_norm': 6.715728759765625, 'learning_rate': 2.462373118655933e-05, 'epoch': 7.61}
|
102 |
+
{'loss': 0.2252, 'grad_norm': 15.648544311523438, 'learning_rate': 2.4332049935830126e-05, 'epoch': 7.7}
|
103 |
+
{'loss': 0.2293, 'grad_norm': 17.969135284423828, 'learning_rate': 2.4040368685100922e-05, 'epoch': 7.79}
|
104 |
+
{'loss': 0.2305, 'grad_norm': 13.376370429992676, 'learning_rate': 2.374868743437172e-05, 'epoch': 7.88}
|
105 |
+
{'loss': 0.2403, 'grad_norm': 8.350042343139648, 'learning_rate': 2.3457006183642515e-05, 'epoch': 7.96}
|
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 sha256:7254aba7a5cb6bd63ec07993a08c616ab7ee580c27261a4a1aa1d849614a3319
|
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 sha256:2e27e3b1bd5bf659298bb37187b6c5138b106564e7ce62bb7749546d65552bfc
|
3 |
+
size 26624
|