mprzibilla
commited on
Commit
•
36fd286
1
Parent(s):
c3799b9
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 +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 sha256:8784c6ab43edf317cbf72cd41edf62484b74352d6d7d83acc2f051f7a65008b2
|
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:fe139ad8af6b60c1a91b2eaa1256fad6cc9d9968a1f8dc94872c4fb95570f04c
|
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 sha256:77449eee0e37c3a473773336c4dbcfe7c14eecc740f7fbaa6436e6669f2d6fbd
|
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 sha256:4cbcf41191e28d7739e96f26098069b589cab9c332419d792a7590cdd6570afd
|
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 sha256:0d68fe7515f9ec06ccc7d9a5fb73e55e1ddd580d17c52369ab12a4688fdb1961
|
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": 26.288,
|
228 |
"eval_steps_per_second": 3.359,
|
229 |
"step": 8710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 10050,
|
233 |
"num_train_epochs": 15,
|
234 |
-
"total_flos": 6.
|
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": 9380,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
227 |
"eval_samples_per_second": 26.288,
|
228 |
"eval_steps_per_second": 3.359,
|
229 |
"step": 8710
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 14.0,
|
233 |
+
"learning_rate": 7.100963552576456e-06,
|
234 |
+
"loss": 0.0617,
|
235 |
+
"step": 9380
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 14.0,
|
239 |
+
"eval_cer": 0.5060606060606061,
|
240 |
+
"eval_loss": 3.7018513679504395,
|
241 |
+
"eval_new_wer": 0.2111111111111111,
|
242 |
+
"eval_old_wer": 0.9055555555555556,
|
243 |
+
"eval_runtime": 6.824,
|
244 |
+
"eval_samples_per_second": 26.378,
|
245 |
+
"eval_steps_per_second": 3.37,
|
246 |
+
"step": 9380
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 10050,
|
250 |
"num_train_epochs": 15,
|
251 |
+
"total_flos": 6.969087095470326e+18,
|
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 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe139ad8af6b60c1a91b2eaa1256fad6cc9d9968a1f8dc94872c4fb95570f04c
|
3 |
size 377646433
|