mprzibilla
commited on
Commit
•
3cbdecf
1
Parent(s):
17074da
Training in progress, epoch 13
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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f1439c871e1b02841474c5218ee60554973fc38e5f6ab02d6e7e4f9ee84027
|
3 |
size 721661957
|
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:ad53e7e3f70cf5a2a8f14b62b3678e6f4f296388bacb21088b6c368bfbc1e724
|
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 sha256:69b56b508055f6baa4848e5aa22ebbf5f82b6fd05f0978276c787a1046c60d19
|
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 sha256:44f9aa74df8a04ce88e3c00f9f8acbaacf956574e776767847039036f627990b
|
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 sha256:1e406ea9fdbb2f2eda25ad91d9386669e7ffcbdb5ce3487b990c808efc783c68
|
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,
|
@@ -210,11 +210,28 @@
|
|
210 |
"eval_samples_per_second": 24.016,
|
211 |
"eval_steps_per_second": 3.088,
|
212 |
"step": 51240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
213 |
}
|
214 |
],
|
215 |
"max_steps": 64050,
|
216 |
"num_train_epochs": 15,
|
217 |
-
"total_flos":
|
218 |
"trial_name": null,
|
219 |
"trial_params": null
|
220 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 55510,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
210 |
"eval_samples_per_second": 24.016,
|
211 |
"eval_steps_per_second": 3.088,
|
212 |
"step": 51240
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 13.0,
|
216 |
+
"learning_rate": 1.4079345253747043e-05,
|
217 |
+
"loss": 0.0714,
|
218 |
+
"step": 55510
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.0,
|
222 |
+
"eval_cer": 0.08398268398268398,
|
223 |
+
"eval_loss": 0.4884723424911499,
|
224 |
+
"eval_new_wer": 0.09523809523809523,
|
225 |
+
"eval_old_wer": 0.14285714285714285,
|
226 |
+
"eval_runtime": 8.4874,
|
227 |
+
"eval_samples_per_second": 24.743,
|
228 |
+
"eval_steps_per_second": 3.181,
|
229 |
+
"step": 55510
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 64050,
|
233 |
"num_train_epochs": 15,
|
234 |
+
"total_flos": 4.205534622878595e+19,
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
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:ad53e7e3f70cf5a2a8f14b62b3678e6f4f296388bacb21088b6c368bfbc1e724
|
3 |
size 377646433
|