mprzibilla
commited on
Commit
•
a120e79
1
Parent(s):
933f1b3
Training in progress, epoch 10
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- 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
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mprzibilla/large_base_M14",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
last-checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mprzibilla/large_base_M14",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
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:ff355af1f436f14af69cf72e30349fe31ed7d8ebc306ea9293b455e84d2dbac8
|
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 sha256:33ae0f6794dbd57dd9708c5c7241acb550fb172e6ed1d61a5fb56117afac8cf0
|
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:a90af717e22c5444ac2780363512011f6b63804ba8ad8c76302c1aac9b4c3b2f
|
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 sha256:6296e004306d9a93205376928c49fe885ae0df076076c6fe0a3514890e58e983
|
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": 25.098,
|
160 |
"eval_steps_per_second": 3.227,
|
161 |
"step": 38430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
}
|
163 |
],
|
164 |
"max_steps": 64050,
|
165 |
"num_train_epochs": 15,
|
166 |
-
"total_flos":
|
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": 25.098,
|
160 |
"eval_steps_per_second": 3.227,
|
161 |
"step": 38430
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 3.5121943202734684e-05,
|
166 |
+
"loss": 0.1317,
|
167 |
+
"step": 42700
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_cer": 0.12034632034632034,
|
172 |
+
"eval_loss": 0.9588236212730408,
|
173 |
+
"eval_new_wer": 0.14761904761904762,
|
174 |
+
"eval_old_wer": 0.20476190476190476,
|
175 |
+
"eval_runtime": 8.5613,
|
176 |
+
"eval_samples_per_second": 24.529,
|
177 |
+
"eval_steps_per_second": 3.154,
|
178 |
+
"step": 42700
|
179 |
}
|
180 |
],
|
181 |
"max_steps": 64050,
|
182 |
"num_train_epochs": 15,
|
183 |
+
"total_flos": 3.235095714199929e+19,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
186 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3451
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfa9fea29b11a29f8df6c7772c40830c4e97d34d0e12405ad9a13dacb99920f3
|
3 |
size 3451
|
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 sha256:33ae0f6794dbd57dd9708c5c7241acb550fb172e6ed1d61a5fb56117afac8cf0
|
3 |
size 377646433
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3451
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfa9fea29b11a29f8df6c7772c40830c4e97d34d0e12405ad9a13dacb99920f3
|
3 |
size 3451
|