mprzibilla
commited on
Commit
•
c0480ea
1
Parent(s):
51fc282
Training in progress, epoch 12
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 +20 -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 174443
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81c4402118ca37116f7bcaf23e62123c8ff6a03ac81036b638145ad2f018ab3e
|
3 |
size 174443
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff3a72597d724c6a55844db672068d5857c6f73c54f3ec41fea7b977c69670e
|
3 |
size 377646433
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a66b1b69510c57c7762b062b648e5360ebd552a9740287944b47daba9d8a5c6f
|
3 |
size 14639
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13a7589714ca42744cc53ba86bd24fc9f77beb3a4a23c480fa17e3779ac95997
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:654ade7d04e771590fa3ef8c680e76a743de642fc942876693f46e319667a40f
|
3 |
size 627
|
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,
|
@@ -193,11 +193,28 @@
|
|
193 |
"eval_samples_per_second": 25.634,
|
194 |
"eval_steps_per_second": 3.296,
|
195 |
"step": 46970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
196 |
}
|
197 |
],
|
198 |
"max_steps": 64050,
|
199 |
"num_train_epochs": 15,
|
200 |
-
"total_flos":
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|
203 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.0,
|
5 |
+
"global_step": 51240,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
193 |
"eval_samples_per_second": 25.634,
|
194 |
"eval_steps_per_second": 3.296,
|
195 |
"step": 46970
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 2.1095188009466215e-05,
|
200 |
+
"loss": 2.8027,
|
201 |
+
"step": 51240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_cer": 0.9575757575757575,
|
206 |
+
"eval_loss": 3.1064510345458984,
|
207 |
+
"eval_new_wer": 0.9333333333333333,
|
208 |
+
"eval_old_wer": 1.0,
|
209 |
+
"eval_runtime": 8.1815,
|
210 |
+
"eval_samples_per_second": 25.668,
|
211 |
+
"eval_steps_per_second": 3.3,
|
212 |
+
"step": 51240
|
213 |
}
|
214 |
],
|
215 |
"max_steps": 64050,
|
216 |
"num_train_epochs": 15,
|
217 |
+
"total_flos": 4.061399854608679e+19,
|
218 |
"trial_name": null,
|
219 |
"trial_params": null
|
220 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff3a72597d724c6a55844db672068d5857c6f73c54f3ec41fea7b977c69670e
|
3 |
size 377646433
|