Training in progress, epoch 7
Browse files
log.txt
CHANGED
@@ -76,3 +76,16 @@
|
|
76 |
{'loss': 0.3802, 'grad_norm': 14.382953643798828, 'learning_rate': 3.07490374518726e-05, 'epoch': 5.78}
|
77 |
{'loss': 0.3861, 'grad_norm': 7.7172627449035645, 'learning_rate': 3.0457356201143393e-05, 'epoch': 5.86}
|
78 |
{'loss': 0.3968, 'grad_norm': 13.746389389038086, 'learning_rate': 3.016567495041419e-05, 'epoch': 5.95}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
{'loss': 0.3802, 'grad_norm': 14.382953643798828, 'learning_rate': 3.07490374518726e-05, 'epoch': 5.78}
|
77 |
{'loss': 0.3861, 'grad_norm': 7.7172627449035645, 'learning_rate': 3.0457356201143393e-05, 'epoch': 5.86}
|
78 |
{'loss': 0.3968, 'grad_norm': 13.746389389038086, 'learning_rate': 3.016567495041419e-05, 'epoch': 5.95}
|
79 |
+
[0 2 2 ... 1 2 1] [0 0 2 ... 0 1 0]
|
80 |
+
{'eval_loss': 2.290968179702759, 'eval_accuracy': 0.40090843891943584, 'eval_runtime': 6.2537, 'eval_samples_per_second': 668.883, 'eval_steps_per_second': 20.948, 'epoch': 6.0}
|
81 |
+
{'loss': 0.3242, 'grad_norm': 5.355894565582275, 'learning_rate': 2.987399369968499e-05, 'epoch': 6.04}
|
82 |
+
{'loss': 0.2491, 'grad_norm': 11.969722747802734, 'learning_rate': 2.9582312448955786e-05, 'epoch': 6.13}
|
83 |
+
{'loss': 0.2627, 'grad_norm': 10.806496620178223, 'learning_rate': 2.9290631198226582e-05, 'epoch': 6.21}
|
84 |
+
{'loss': 0.2674, 'grad_norm': 11.133452415466309, 'learning_rate': 2.899894994749738e-05, 'epoch': 6.3}
|
85 |
+
{'loss': 0.2795, 'grad_norm': 10.295939445495605, 'learning_rate': 2.8707268696768175e-05, 'epoch': 6.39}
|
86 |
+
{'loss': 0.28, 'grad_norm': 16.589740753173828, 'learning_rate': 2.8415587446038972e-05, 'epoch': 6.48}
|
87 |
+
{'loss': 0.28, 'grad_norm': 21.517580032348633, 'learning_rate': 2.812390619530977e-05, 'epoch': 6.56}
|
88 |
+
{'loss': 0.2861, 'grad_norm': 14.851978302001953, 'learning_rate': 2.7832224944580565e-05, 'epoch': 6.65}
|
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}
|
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:c82fa030ef33724fb390346f4505df82e103316f7c2779e9edc4784ff8f45edf
|
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 sha256:0e5bbd10b00faae8318b6be43297ab49966141b45cc10dde4d99b734667ce5ca
|
3 |
+
size 23930
|