Commit
•
a043665
1
Parent(s):
c29a81e
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 174443
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca348af9a550d6c00e1a5c1c40e8fe639473952c4d226ef818caca863813eb5
|
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 sha256:363021e64044afd3b8636a6b765d5a14af1bd244897f2524374369b6e4bb1aaa
|
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 sha256:9cc719fc93e1931715a8ff325ea84f2941737c64bb783e06000500e3c1275c32
|
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 sha256:7e768eb8da7460b6f20d59bf42eabf78efc7270c18c6b15605c48be27382c4c4
|
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": 26.735,
|
194 |
"eval_steps_per_second": 3.437,
|
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": 26.735,
|
194 |
"eval_steps_per_second": 3.437,
|
195 |
"step": 46970
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 12.0,
|
199 |
+
"learning_rate": 2.1093544570076258e-05,
|
200 |
+
"loss": 2.8215,
|
201 |
+
"step": 51240
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 12.0,
|
205 |
+
"eval_cer": 0.9601731601731601,
|
206 |
+
"eval_loss": 3.1361286640167236,
|
207 |
+
"eval_new_wer": 0.9380952380952381,
|
208 |
+
"eval_old_wer": 1.0,
|
209 |
+
"eval_runtime": 7.7971,
|
210 |
+
"eval_samples_per_second": 26.933,
|
211 |
+
"eval_steps_per_second": 3.463,
|
212 |
+
"step": 51240
|
213 |
}
|
214 |
],
|
215 |
"max_steps": 64050,
|
216 |
"num_train_epochs": 15,
|
217 |
+
"total_flos": 4.062359675319509e+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 sha256:363021e64044afd3b8636a6b765d5a14af1bd244897f2524374369b6e4bb1aaa
|
3 |
size 377646433
|