mprzibilla
commited on
Commit
•
2834f21
1
Parent(s):
eb54918
Training in progress, epoch 10
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:fe70863d43106486679817d5f4722793a266f59fefb954f27cfaa5cdb234bd62
|
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 sha256:90da37e1dc5f0added8b1434d65fceab165f2d87dc1cf728c28cead2fff56f27
|
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:fb3248809097ac54ff3da5b23f091689b9bb32f4864f3e81b50faaeeeb4db31c
|
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 sha256:02ce2f9fe735d779e0a5267ebe67c92b57c3d47a041f8cd2520e58d5b41adb64
|
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:bac1bcbb3ae49600bd605411d43c52aad0cd59906fc218b43d15bae27fa4fbfe
|
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,
|
@@ -159,11 +159,28 @@
|
|
159 |
"eval_samples_per_second": 27.155,
|
160 |
"eval_steps_per_second": 3.491,
|
161 |
"step": 38430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 64050,
|
165 |
"num_train_epochs": 15,
|
166 |
-
"total_flos": 3.
|
167 |
"trial_name": null,
|
168 |
"trial_params": null
|
169 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 42700,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
159 |
"eval_samples_per_second": 27.155,
|
160 |
"eval_steps_per_second": 3.491,
|
161 |
"step": 38430
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 3.5121943202734684e-05,
|
166 |
+
"loss": 0.1179,
|
167 |
+
"step": 42700
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_cer": 0.1264069264069264,
|
172 |
+
"eval_loss": 1.0122177600860596,
|
173 |
+
"eval_new_wer": 0.1523809523809524,
|
174 |
+
"eval_old_wer": 0.18095238095238095,
|
175 |
+
"eval_runtime": 7.7665,
|
176 |
+
"eval_samples_per_second": 27.039,
|
177 |
+
"eval_steps_per_second": 3.476,
|
178 |
+
"step": 42700
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 64050,
|
182 |
"num_train_epochs": 15,
|
183 |
+
"total_flos": 3.384789758227452e+19,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
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 sha256:90da37e1dc5f0added8b1434d65fceab165f2d87dc1cf728c28cead2fff56f27
|
3 |
size 377646433
|