mprzibilla
commited on
Commit
•
17074da
1
Parent(s):
eb0dcff
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 +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 721661957
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bac7ecda0c7de9178cd6fb9b1c30ee9823e31a7de4113fedc6918ee384701c37
|
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 sha256:76b5cd3b5e3a732c0f0d0874b3b59f2b8ec7a4a34ea18d6155a009c32c5adcc9
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c302ba39f8300a3dc64ffd978db228aba43825715bdaf7ddd35eed7903b135
|
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:d41519051c374190ccc64fc564878f51e41e25d621689e6b3c5b61f710b45cc4
|
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:f8a8736fbf065bb57c14d67cb4f7ef16a8ca9f4bb49c763e34f074eefcc1efc0
|
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": 24.597,
|
194 |
"eval_steps_per_second": 3.162,
|
195 |
"step": 46970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
196 |
}
|
197 |
],
|
198 |
"max_steps": 64050,
|
199 |
"num_train_epochs": 15,
|
200 |
-
"total_flos": 3.
|
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": 24.597,
|
194 |
"eval_steps_per_second": 3.162,
|
195 |
"step": 46970
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 2.1093544570076258e-05,
|
200 |
+
"loss": 0.0892,
|
201 |
+
"step": 51240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_cer": 0.10043290043290043,
|
206 |
+
"eval_loss": 0.7190653681755066,
|
207 |
+
"eval_new_wer": 0.11428571428571428,
|
208 |
+
"eval_old_wer": 0.16666666666666666,
|
209 |
+
"eval_runtime": 8.7441,
|
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": 3.881704743918667e+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 sha256:76b5cd3b5e3a732c0f0d0874b3b59f2b8ec7a4a34ea18d6155a009c32c5adcc9
|
3 |
size 377646433
|