mprzibilla
commited on
Commit
•
8ca518a
1
Parent(s):
051729c
Training in progress, epoch 15
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 174443
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0d104d12fcba473803cd92a7a6d95cb599ca78a30477b13e821de229b167eb2
|
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 sha256:475c39cdd77a8817d80b8ce92895ebf327560809a6aa576412d0e47fc44640ea
|
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:c1069b7ffb3af89aa9f6f909347d8a8ba457c5127aa1618d6ba97e41c8338d5f
|
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:cd85e6925db532c90189f692b2f0f1298783085988225664c736f8375ef72259
|
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:f7d484bda8662d5924e77e9c3adf8243651dda16cab0b0e4af661e33593c9276
|
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,
|
@@ -244,11 +244,28 @@
|
|
244 |
"eval_samples_per_second": 22.796,
|
245 |
"eval_steps_per_second": 2.931,
|
246 |
"step": 59780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 64050,
|
250 |
"num_train_epochs": 15,
|
251 |
-
"total_flos":
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 64050,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 22.796,
|
245 |
"eval_steps_per_second": 2.931,
|
246 |
"step": 59780
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 5.094662108861425e-08,
|
251 |
+
"loss": 2.7903,
|
252 |
+
"step": 64050
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.9575757575757575,
|
257 |
+
"eval_loss": 3.104132890701294,
|
258 |
+
"eval_new_wer": 0.9333333333333333,
|
259 |
+
"eval_old_wer": 1.0,
|
260 |
+
"eval_runtime": 8.8255,
|
261 |
+
"eval_samples_per_second": 23.795,
|
262 |
+
"eval_steps_per_second": 3.059,
|
263 |
+
"step": 64050
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 64050,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 5.076674134512955e+19,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
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 sha256:475c39cdd77a8817d80b8ce92895ebf327560809a6aa576412d0e47fc44640ea
|
3 |
size 377646433
|