Training in progress, epoch 13
Browse files
log.txt
CHANGED
@@ -157,3 +157,16 @@
|
|
157 |
{'loss': 0.0976, 'grad_norm': 1.1808760166168213, 'learning_rate': 1.0623031151557579e-05, 'epoch': 11.81}
|
158 |
{'loss': 0.1075, 'grad_norm': 10.200865745544434, 'learning_rate': 1.0331349900828375e-05, 'epoch': 11.9}
|
159 |
{'loss': 0.1027, 'grad_norm': 7.143473148345947, 'learning_rate': 1.0039668650099172e-05, 'epoch': 11.99}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
{'loss': 0.0976, 'grad_norm': 1.1808760166168213, 'learning_rate': 1.0623031151557579e-05, 'epoch': 11.81}
|
158 |
{'loss': 0.1075, 'grad_norm': 10.200865745544434, 'learning_rate': 1.0331349900828375e-05, 'epoch': 11.9}
|
159 |
{'loss': 0.1027, 'grad_norm': 7.143473148345947, 'learning_rate': 1.0039668650099172e-05, 'epoch': 11.99}
|
160 |
+
[0 2 2 ... 0 2 0] [0 0 2 ... 0 1 0]
|
161 |
+
{'eval_loss': 4.681421279907227, 'eval_accuracy': 0.41238345684915134, 'eval_runtime': 6.4322, 'eval_samples_per_second': 650.321, 'eval_steps_per_second': 20.366, 'epoch': 12.0}
|
162 |
+
{'loss': 0.0806, 'grad_norm': 17.015737533569336, 'learning_rate': 9.74798739936997e-06, 'epoch': 12.08}
|
163 |
+
{'loss': 0.0886, 'grad_norm': 28.621715545654297, 'learning_rate': 9.456306148640766e-06, 'epoch': 12.16}
|
164 |
+
{'loss': 0.0864, 'grad_norm': 16.31233787536621, 'learning_rate': 9.164624897911563e-06, 'epoch': 12.25}
|
165 |
+
{'loss': 0.0828, 'grad_norm': 4.050362586975098, 'learning_rate': 8.87294364718236e-06, 'epoch': 12.34}
|
166 |
+
{'loss': 0.0793, 'grad_norm': 0.744445264339447, 'learning_rate': 8.581262396453156e-06, 'epoch': 12.43}
|
167 |
+
{'loss': 0.0959, 'grad_norm': 14.591256141662598, 'learning_rate': 8.289581145723952e-06, 'epoch': 12.51}
|
168 |
+
{'loss': 0.0883, 'grad_norm': 14.431562423706055, 'learning_rate': 7.99789989499475e-06, 'epoch': 12.6}
|
169 |
+
{'loss': 0.0883, 'grad_norm': 13.123093605041504, 'learning_rate': 7.706218644265547e-06, 'epoch': 12.69}
|
170 |
+
{'loss': 0.0889, 'grad_norm': 32.98908996582031, 'learning_rate': 7.414537393536344e-06, 'epoch': 12.78}
|
171 |
+
{'loss': 0.0837, 'grad_norm': 0.6928532719612122, 'learning_rate': 7.1228561428071415e-06, 'epoch': 12.86}
|
172 |
+
{'loss': 0.0897, 'grad_norm': 26.65106773376465, 'learning_rate': 6.831174892077938e-06, 'epoch': 12.95}
|
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 sha256:7f255ef9e96b68d315888f1664a94af59595316c1367181d81a21b8ed782e5c8
|
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 sha256:8a495dd63df50de05aca5a3a97ec3d021a676894722d9d297d68ef91dc6a9a2b
|
3 |
+
size 40524
|