mprzibilla
commited on
Commit
•
24aa983
1
Parent(s):
3af261b
Training in progress, epoch 14
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 +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 721668101
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4c8ebc4689e85c6fcb2eab15f58bc24d287abff69dd8b3c5537ad5177cadb6b
|
3 |
size 721668101
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704f18eb157e5fdddcd657f6f66a7e2e64a842a1eee7d0697aea5b3b7bde43a5
|
3 |
size 377649505
|
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 sha256:07abb9d9dd70e530b651febef93da023123d8a5b91b28240e9343f8850ae7ac9
|
3 |
+
size 14575
|
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 sha256:157a0bb494b20f1cedb74d3808cc7e68aaebd96975182a95b44c030885000b52
|
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 sha256:833481975eb525b56595507c22a4cbdc6b9c456f424a9bdb6802b6b084322c22
|
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,
|
@@ -227,11 +227,28 @@
|
|
227 |
"eval_samples_per_second": 27.111,
|
228 |
"eval_steps_per_second": 3.486,
|
229 |
"step": 17407
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 20085,
|
233 |
"num_train_epochs": 15,
|
234 |
-
"total_flos": 1.
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.0,
|
5 |
+
"global_step": 18746,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
227 |
"eval_samples_per_second": 27.111,
|
228 |
"eval_steps_per_second": 3.486,
|
229 |
"step": 17407
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 14.0,
|
233 |
+
"learning_rate": 7.0751008856978145e-06,
|
234 |
+
"loss": 0.0385,
|
235 |
+
"step": 18746
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 14.0,
|
239 |
+
"eval_cer": 0.129004329004329,
|
240 |
+
"eval_loss": 1.4713504314422607,
|
241 |
+
"eval_new_wer": 0.12857142857142856,
|
242 |
+
"eval_old_wer": 0.2523809523809524,
|
243 |
+
"eval_runtime": 7.8845,
|
244 |
+
"eval_samples_per_second": 26.635,
|
245 |
+
"eval_steps_per_second": 3.424,
|
246 |
+
"step": 18746
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 20085,
|
250 |
"num_train_epochs": 15,
|
251 |
+
"total_flos": 1.4230274250443813e+19,
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377649505
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:704f18eb157e5fdddcd657f6f66a7e2e64a842a1eee7d0697aea5b3b7bde43a5
|
3 |
size 377649505
|