Training in progress, epoch 11
Browse files
log.txt
CHANGED
@@ -130,3 +130,16 @@
|
|
130 |
{'loss': 0.1422, 'grad_norm': 12.243080139160156, 'learning_rate': 1.733169991832925e-05, 'epoch': 9.8}
|
131 |
{'loss': 0.1515, 'grad_norm': 8.44780158996582, 'learning_rate': 1.7040018667600048e-05, 'epoch': 9.89}
|
132 |
{'loss': 0.1478, 'grad_norm': 7.068332672119141, 'learning_rate': 1.6748337416870844e-05, 'epoch': 9.98}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
130 |
{'loss': 0.1422, 'grad_norm': 12.243080139160156, 'learning_rate': 1.733169991832925e-05, 'epoch': 9.8}
|
131 |
{'loss': 0.1515, 'grad_norm': 8.44780158996582, 'learning_rate': 1.7040018667600048e-05, 'epoch': 9.89}
|
132 |
{'loss': 0.1478, 'grad_norm': 7.068332672119141, 'learning_rate': 1.6748337416870844e-05, 'epoch': 9.98}
|
133 |
+
[0 2 2 ... 1 2 0] [0 0 2 ... 0 1 0]
|
134 |
+
{'eval_loss': 3.569014072418213, 'eval_accuracy': 0.4056896963901506, 'eval_runtime': 6.3752, 'eval_samples_per_second': 656.14, 'eval_steps_per_second': 20.549, 'epoch': 10.0}
|
135 |
+
{'loss': 0.1227, 'grad_norm': 12.944316864013672, 'learning_rate': 1.645665616614164e-05, 'epoch': 10.06}
|
136 |
+
{'loss': 0.1165, 'grad_norm': 23.897483825683594, 'learning_rate': 1.6164974915412437e-05, 'epoch': 10.15}
|
137 |
+
{'loss': 0.1105, 'grad_norm': 7.69583797454834, 'learning_rate': 1.5873293664683234e-05, 'epoch': 10.24}
|
138 |
+
{'loss': 0.1159, 'grad_norm': 13.00390338897705, 'learning_rate': 1.5581612413954034e-05, 'epoch': 10.33}
|
139 |
+
{'loss': 0.115, 'grad_norm': 9.015633583068848, 'learning_rate': 1.528993116322483e-05, 'epoch': 10.41}
|
140 |
+
{'loss': 0.1207, 'grad_norm': 12.009922981262207, 'learning_rate': 1.4998249912495627e-05, 'epoch': 10.5}
|
141 |
+
{'loss': 0.1227, 'grad_norm': 19.245769500732422, 'learning_rate': 1.4706568661766423e-05, 'epoch': 10.59}
|
142 |
+
{'loss': 0.1204, 'grad_norm': 15.714821815490723, 'learning_rate': 1.441488741103722e-05, 'epoch': 10.68}
|
143 |
+
{'loss': 0.1227, 'grad_norm': 5.548469543457031, 'learning_rate': 1.4123206160308016e-05, 'epoch': 10.76}
|
144 |
+
{'loss': 0.1164, 'grad_norm': 10.179027557373047, 'learning_rate': 1.3831524909578814e-05, 'epoch': 10.85}
|
145 |
+
{'loss': 0.1231, 'grad_norm': 1.8333979845046997, 'learning_rate': 1.353984365884961e-05, 'epoch': 10.94}
|
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:f8bdb3b720846e729135e1095d07d399c6310735d2d24571888b5d89cb3b2d9d
|
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:ad46e3e81d9ee7932c3f9fa5dcc82efe318505380f78d1bd9047c5ad1b43aac3
|
3 |
+
size 34921
|