mprzibilla
commited on
Commit
•
dd28337
1
Parent(s):
a043665
Training in progress, epoch 13
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:bb0b6b9ea6d499af5d5b4a1a46b1131c1b9409f2fa43a90395a54db87ab53ee5
|
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 sha256:345d6e0a4db5e43f2fb105d9941865403a8507c560a2d5710841d0a7b6298825
|
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 sha256:256fc5a299bfe8054ae29687bd65e00b9d44ccb79b9f96a9438c881a71f8b712
|
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 sha256:800438eb5cd2bc2700d0cf4002e254d4b1f15afcf81edf80b2d12edb5382ffdf
|
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 sha256:1e406ea9fdbb2f2eda25ad91d9386669e7ffcbdb5ce3487b990c808efc783c68
|
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,
|
@@ -210,11 +210,28 @@
|
|
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.
|
218 |
"trial_name": null,
|
219 |
"trial_params": null
|
220 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.0,
|
5 |
+
"global_step": 55510,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
210 |
"eval_samples_per_second": 26.933,
|
211 |
"eval_steps_per_second": 3.463,
|
212 |
"step": 51240
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 13.0,
|
216 |
+
"learning_rate": 1.4079345253747043e-05,
|
217 |
+
"loss": 2.8178,
|
218 |
+
"step": 55510
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 13.0,
|
222 |
+
"eval_cer": 0.9567099567099567,
|
223 |
+
"eval_loss": 3.1265242099761963,
|
224 |
+
"eval_new_wer": 0.9285714285714286,
|
225 |
+
"eval_old_wer": 1.0,
|
226 |
+
"eval_runtime": 7.8518,
|
227 |
+
"eval_samples_per_second": 26.746,
|
228 |
+
"eval_steps_per_second": 3.439,
|
229 |
+
"step": 55510
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 64050,
|
233 |
"num_train_epochs": 15,
|
234 |
+
"total_flos": 4.401354286546484e+19,
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
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 sha256:345d6e0a4db5e43f2fb105d9941865403a8507c560a2d5710841d0a7b6298825
|
3 |
size 377646433
|