Commit
•
26f41c7
1
Parent(s):
333863f
Training in progress, step 147750
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- 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 sha256:7e3b65c7bc1d88b01cd70cca190ad45bfa2c426bb24413d3d5888e0de89b6e75
|
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:b271b735cca5898216191c5715af5693f73f7bbd4a4782310e07579fdd145d99
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f05ff0056f56dda13e32efba5a9e37093294a44e0eac3acb2211e2a0d551e893
|
3 |
+
size 14631
|
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 sha256:36685f4552759f6cc309ca64e8cce9adf0df6fc74825ff8e184d999bfd278125
|
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:e8e50cfa3e91bfb320537d16c31fab9efeb3589bc04f7168987f8efcac47acb9
|
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,
|
@@ -150,11 +150,27 @@
|
|
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.
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 250.0,
|
5 |
+
"global_step": 147750,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_steps_per_second": 25.746,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 132975
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 250.0,
|
156 |
+
"learning_rate": 4.9870692418942315e-08,
|
157 |
+
"loss": 2.8383,
|
158 |
+
"step": 147750
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 250.0,
|
162 |
+
"eval_cer": 0.998989898989899,
|
163 |
+
"eval_loss": 3.508450746536255,
|
164 |
+
"eval_runtime": 0.8884,
|
165 |
+
"eval_samples_per_second": 202.619,
|
166 |
+
"eval_steps_per_second": 25.89,
|
167 |
+
"eval_wer": 1.0,
|
168 |
+
"step": 147750
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 147750,
|
172 |
"num_train_epochs": 250,
|
173 |
+
"total_flos": 1.4263798622905591e+20,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
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:b271b735cca5898216191c5715af5693f73f7bbd4a4782310e07579fdd145d99
|
3 |
size 377644503
|