Training in progress, epoch 29
Browse files
log.txt
CHANGED
@@ -204,3 +204,18 @@
|
|
204 |
{'loss': 0.0428, 'grad_norm': 10.590956687927246, 'learning_rate': 2.3398669933496677e-05, 'epoch': 26.6}
|
205 |
{'loss': 0.0449, 'grad_norm': 15.461783409118652, 'learning_rate': 2.3223661183059154e-05, 'epoch': 26.78}
|
206 |
{'loss': 0.0463, 'grad_norm': 9.42243480682373, 'learning_rate': 2.304865243262163e-05, 'epoch': 26.95}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
{'loss': 0.0428, 'grad_norm': 10.590956687927246, 'learning_rate': 2.3398669933496677e-05, 'epoch': 26.6}
|
205 |
{'loss': 0.0449, 'grad_norm': 15.461783409118652, 'learning_rate': 2.3223661183059154e-05, 'epoch': 26.78}
|
206 |
{'loss': 0.0463, 'grad_norm': 9.42243480682373, 'learning_rate': 2.304865243262163e-05, 'epoch': 26.95}
|
207 |
+
[3 2 1 ... 3 1 0] [0 0 2 ... 0 1 0]
|
208 |
+
{'eval_loss': 5.401566028594971, 'eval_accuracy': 0.4150131484580445, 'eval_runtime': 5.1892, 'eval_samples_per_second': 806.096, 'eval_steps_per_second': 12.719, 'epoch': 27.0}
|
209 |
+
{'loss': 0.0376, 'grad_norm': 3.698101043701172, 'learning_rate': 2.2873643682184108e-05, 'epoch': 27.13}
|
210 |
+
{'loss': 0.0379, 'grad_norm': 11.145508766174316, 'learning_rate': 2.269863493174659e-05, 'epoch': 27.3}
|
211 |
+
{'loss': 0.0411, 'grad_norm': 1.2739465236663818, 'learning_rate': 2.2523626181309066e-05, 'epoch': 27.48}
|
212 |
+
{'loss': 0.0397, 'grad_norm': 0.7999504208564758, 'learning_rate': 2.2348617430871543e-05, 'epoch': 27.65}
|
213 |
+
{'loss': 0.043, 'grad_norm': 0.1800367683172226, 'learning_rate': 2.217360868043402e-05, 'epoch': 27.83}
|
214 |
+
[3 3 1 ... 0 1 0] [0 0 2 ... 0 1 0]
|
215 |
+
{'eval_loss': 5.35640811920166, 'eval_accuracy': 0.41190533110207983, 'eval_runtime': 5.0585, 'eval_samples_per_second': 826.922, 'eval_steps_per_second': 13.047, 'epoch': 28.0}
|
216 |
+
{'loss': 0.0421, 'grad_norm': 14.743362426757812, 'learning_rate': 2.19985999299965e-05, 'epoch': 28.0}
|
217 |
+
{'loss': 0.0352, 'grad_norm': 8.293474197387695, 'learning_rate': 2.182359117955898e-05, 'epoch': 28.18}
|
218 |
+
{'loss': 0.0375, 'grad_norm': 0.09835419803857803, 'learning_rate': 2.164858242912146e-05, 'epoch': 28.35}
|
219 |
+
{'loss': 0.0406, 'grad_norm': 1.9000002145767212, 'learning_rate': 2.1473573678683936e-05, 'epoch': 28.53}
|
220 |
+
{'loss': 0.039, 'grad_norm': 3.016406774520874, 'learning_rate': 2.1298564928246413e-05, 'epoch': 28.7}
|
221 |
+
{'loss': 0.0412, 'grad_norm': 5.020988941192627, 'learning_rate': 2.1123556177808894e-05, 'epoch': 28.88}
|
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:aa3481e24f829a9e54385133cd7e4f94d3dfa76527e1a1b271e925bf7eb6600c
|
3 |
size 267829484
|
runs/Mar13_17-26-31_cehsc-app-001.ad.unlv.edu/events.out.tfevents.1710375994.cehsc-app-001.ad.unlv.edu.3270813.0
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:c4e8b02233580d936a0de070474caddf85e4808624bd07c90cad6590224a9357
|
3 |
+
size 49533
|