Training in progress, epoch 12
Browse files
log.txt
CHANGED
@@ -143,3 +143,17 @@
|
|
143 |
{'loss': 1.387, 'grad_norm': 1.6413313150405884, 'learning_rate': 3.9236961848092406e-05, 'epoch': 10.76}
|
144 |
{'loss': 1.3864, 'grad_norm': 1.5505764484405518, 'learning_rate': 3.914945747287364e-05, 'epoch': 10.85}
|
145 |
{'loss': 1.3866, 'grad_norm': 1.60427987575531, 'learning_rate': 3.906195309765489e-05, 'epoch': 10.94}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
{'loss': 1.387, 'grad_norm': 1.6413313150405884, 'learning_rate': 3.9236961848092406e-05, 'epoch': 10.76}
|
144 |
{'loss': 1.3864, 'grad_norm': 1.5505764484405518, 'learning_rate': 3.914945747287364e-05, 'epoch': 10.85}
|
145 |
{'loss': 1.3866, 'grad_norm': 1.60427987575531, 'learning_rate': 3.906195309765489e-05, 'epoch': 10.94}
|
146 |
+
[0 0 0 ... 0 2 0] [0 0 2 ... 0 1 0]
|
147 |
+
{'eval_loss': 1.3862946033477783, 'eval_accuracy': 0.2773129333014583, 'eval_runtime': 31.5172, 'eval_samples_per_second': 132.721, 'eval_steps_per_second': 4.156, 'epoch': 11.0}
|
148 |
+
{'loss': 1.3869, 'grad_norm': 1.7129335403442383, 'learning_rate': 3.8974448722436124e-05, 'epoch': 11.03}
|
149 |
+
{'loss': 1.3863, 'grad_norm': 1.2940468788146973, 'learning_rate': 3.888694434721736e-05, 'epoch': 11.11}
|
150 |
+
{'loss': 1.3864, 'grad_norm': 1.6037455797195435, 'learning_rate': 3.8799439971998605e-05, 'epoch': 11.2}
|
151 |
+
{'loss': 1.3872, 'grad_norm': 1.6535574197769165, 'learning_rate': 3.871193559677984e-05, 'epoch': 11.29}
|
152 |
+
{'loss': 1.3864, 'grad_norm': 1.4949287176132202, 'learning_rate': 3.862443122156108e-05, 'epoch': 11.38}
|
153 |
+
{'loss': 1.387, 'grad_norm': 1.5116932392120361, 'learning_rate': 3.853692684634232e-05, 'epoch': 11.46}
|
154 |
+
{'loss': 1.3866, 'grad_norm': 1.4328763484954834, 'learning_rate': 3.844942247112356e-05, 'epoch': 11.55}
|
155 |
+
{'loss': 1.3869, 'grad_norm': 1.5736273527145386, 'learning_rate': 3.8361918095904796e-05, 'epoch': 11.64}
|
156 |
+
{'loss': 1.3867, 'grad_norm': 1.7489657402038574, 'learning_rate': 3.827441372068604e-05, 'epoch': 11.73}
|
157 |
+
{'loss': 1.3866, 'grad_norm': 1.4763479232788086, 'learning_rate': 3.8186909345467276e-05, 'epoch': 11.81}
|
158 |
+
{'loss': 1.3868, 'grad_norm': 1.4320505857467651, 'learning_rate': 3.809940497024851e-05, 'epoch': 11.9}
|
159 |
+
{'loss': 1.3869, 'grad_norm': 1.6347980499267578, 'learning_rate': 3.801190059502975e-05, 'epoch': 11.99}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ac4b8f936b832f6fc8c325c10c5d08617fa1ba710f16413a33862d795c6fd29
|
3 |
size 1340618660
|
runs/Mar14_00-20-30_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710400834.cehsc-app-001.ad.unlv.edu.3751445.0
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 sha256:0620ee5406c76c9fafeeb98beb88d1a33dfb6bafd004d566318dcb2033001649
|
3 |
+
size 37933
|