Training in progress, epoch 13
Browse files
log.txt
CHANGED
@@ -157,3 +157,16 @@
|
|
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}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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}
|
160 |
+
[0 0 0 ... 0 0 0] [0 0 2 ... 0 1 0]
|
161 |
+
{'eval_loss': 1.3862946033477783, 'eval_accuracy': 0.3160411188142481, 'eval_runtime': 31.2795, 'eval_samples_per_second': 133.73, 'eval_steps_per_second': 4.188, 'epoch': 12.0}
|
162 |
+
{'loss': 1.3869, 'grad_norm': 1.5249700546264648, 'learning_rate': 3.7924396219810994e-05, 'epoch': 12.08}
|
163 |
+
{'loss': 1.387, 'grad_norm': 1.2788211107254028, 'learning_rate': 3.783689184459223e-05, 'epoch': 12.16}
|
164 |
+
{'loss': 1.3868, 'grad_norm': 1.6066429615020752, 'learning_rate': 3.774938746937347e-05, 'epoch': 12.25}
|
165 |
+
{'loss': 1.3869, 'grad_norm': 1.2969735860824585, 'learning_rate': 3.766188309415471e-05, 'epoch': 12.34}
|
166 |
+
{'loss': 1.3867, 'grad_norm': 1.5080153942108154, 'learning_rate': 3.757437871893595e-05, 'epoch': 12.43}
|
167 |
+
{'loss': 1.387, 'grad_norm': 1.6393741369247437, 'learning_rate': 3.7486874343717185e-05, 'epoch': 12.51}
|
168 |
+
{'loss': 1.3866, 'grad_norm': 1.464860439300537, 'learning_rate': 3.739936996849843e-05, 'epoch': 12.6}
|
169 |
+
{'loss': 1.3869, 'grad_norm': 1.5701706409454346, 'learning_rate': 3.7311865593279666e-05, 'epoch': 12.69}
|
170 |
+
{'loss': 1.3863, 'grad_norm': 1.479953408241272, 'learning_rate': 3.72243612180609e-05, 'epoch': 12.78}
|
171 |
+
{'loss': 1.3865, 'grad_norm': 1.6790354251861572, 'learning_rate': 3.7136856842842146e-05, 'epoch': 12.86}
|
172 |
+
{'loss': 1.3867, 'grad_norm': 1.5029643774032593, 'learning_rate': 3.7049352467623383e-05, 'epoch': 12.95}
|
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:e1e945eded61d566be42cfbfa8fb67d414451761800f19ae7a1c72f17ee64da3
|
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 sha256:05a919325fee447c7461358c5bbc73eda8792499bf05f5a0491f6677a22b985f
|
3 |
+
size 40627
|