mprzibilla
commited on
Commit
•
333863f
1
Parent(s):
daab630
Training in progress, step 132975
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 174303
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c734ce443d14976ee0e61a2000d7b263f86054b0eab2513c2ce30a4d8e10ca
|
3 |
size 174303
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cab0acf627be19a73632282036da1eb6126ac9858141b3d4dfd3f1ee2518160
|
3 |
size 377644503
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2e1fbfd521af25cba8115082dc72e036c6e807de22d01ae6ddb162f2ea67895
|
3 |
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28538ababd57f765f59e9aec82d6724d600ccd500f0fcc0a2626b901a4318d8c
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdf8e5b4e2fbdebf317cff5ed55369f85f25a4ec900820d361ba8599e3967d3f
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -134,11 +134,27 @@
|
|
134 |
"eval_steps_per_second": 25.672,
|
135 |
"eval_wer": 1.0,
|
136 |
"step": 118200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
137 |
}
|
138 |
],
|
139 |
"max_steps": 147750,
|
140 |
"num_train_epochs": 250,
|
141 |
-
"total_flos": 1.
|
142 |
"trial_name": null,
|
143 |
"trial_params": null
|
144 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 225.0,
|
5 |
+
"global_step": 132975,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
134 |
"eval_steps_per_second": 25.672,
|
135 |
"eval_wer": 1.0,
|
136 |
"step": 118200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 225.0,
|
140 |
+
"learning_rate": 1.0571161915889516e-05,
|
141 |
+
"loss": 2.8407,
|
142 |
+
"step": 132975
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 225.0,
|
146 |
+
"eval_cer": 0.998989898989899,
|
147 |
+
"eval_loss": 3.5073866844177246,
|
148 |
+
"eval_runtime": 0.8933,
|
149 |
+
"eval_samples_per_second": 201.494,
|
150 |
+
"eval_steps_per_second": 25.746,
|
151 |
+
"eval_wer": 1.0,
|
152 |
+
"step": 132975
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 147750,
|
156 |
"num_train_epochs": 250,
|
157 |
+
"total_flos": 1.2836404949989217e+20,
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7cab0acf627be19a73632282036da1eb6126ac9858141b3d4dfd3f1ee2518160
|
3 |
size 377644503
|