mprzibilla
commited on
Commit
•
c29a81e
1
Parent(s):
17e7023
Training in progress, epoch 11
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:d67ba69be610651d0b10132fb8b4b5e18d9162b98d6c5c8e27e05e77efe8d6fd
|
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:ec56b163ed691fb1d538fc222b2444129e57a9435044d961e77e311076f0746c
|
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 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e71cb7e15f3ef6947560bfce04d1f67f6fe7ef4426b5c18662b7a8e083724f41
|
3 |
size 14575
|
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 sha256:859f7accb36343c67a74c7b9d63d394fbd80dc9a6fe36d6bdfecdad339f98061
|
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 sha256:818f63b0c2aa872223e455194f13d9fe3813631db86d4483bcb5a709538ca178
|
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,
|
@@ -176,11 +176,28 @@
|
|
176 |
"eval_samples_per_second": 26.968,
|
177 |
"eval_steps_per_second": 3.467,
|
178 |
"step": 42700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 64050,
|
182 |
"num_train_epochs": 15,
|
183 |
-
"total_flos": 3.
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 11.0,
|
5 |
+
"global_step": 46970,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
176 |
"eval_samples_per_second": 26.968,
|
177 |
"eval_steps_per_second": 3.467,
|
178 |
"step": 42700
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 2.8107743886405467e-05,
|
183 |
+
"loss": 2.8301,
|
184 |
+
"step": 46970
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_cer": 0.9601731601731601,
|
189 |
+
"eval_loss": 3.141080141067505,
|
190 |
+
"eval_new_wer": 0.9333333333333333,
|
191 |
+
"eval_old_wer": 1.0,
|
192 |
+
"eval_runtime": 7.8547,
|
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": 3.722634324457703e+19,
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|
203 |
}
|
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:ec56b163ed691fb1d538fc222b2444129e57a9435044d961e77e311076f0746c
|
3 |
size 377646433
|