mprzibilla
commited on
Commit
•
5e37ec6
1
Parent(s):
2834f21
Training in progress, epoch 11
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 +1 -1
- 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 sha256:9b23f1df616fc0c3bd4596c9919b57bc7fb4a9bdf18d719609dc3ce5171980e2
|
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:f0484663c13803976a0c03ccc8b90c3c50e07ca8e816cc820ec131cc9d821fc2
|
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:e36decda55e4f1e3da402f536580e5e07aceccb7699ca939e538c0c4931e45c2
|
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:a0d5fff130724d127477ebb43eacd79fe6a01e4a3241dd4098f37c94a8fcd5e2
|
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": 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.
|
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": 27.039,
|
177 |
"eval_steps_per_second": 3.476,
|
178 |
"step": 42700
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 11.0,
|
182 |
+
"learning_rate": 2.8106100447015514e-05,
|
183 |
+
"loss": 0.0987,
|
184 |
+
"step": 46970
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 11.0,
|
188 |
+
"eval_cer": 0.08831168831168831,
|
189 |
+
"eval_loss": 0.7208192944526672,
|
190 |
+
"eval_new_wer": 0.0761904761904762,
|
191 |
+
"eval_old_wer": 0.14285714285714285,
|
192 |
+
"eval_runtime": 7.7985,
|
193 |
+
"eval_samples_per_second": 26.928,
|
194 |
+
"eval_steps_per_second": 3.462,
|
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 |
}
|
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:bffa79e84b4c5697fa282520d8a0bbcd0e913e1969ff4bbeead38d352047c976
|
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:f0484663c13803976a0c03ccc8b90c3c50e07ca8e816cc820ec131cc9d821fc2
|
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:bffa79e84b4c5697fa282520d8a0bbcd0e913e1969ff4bbeead38d352047c976
|
3 |
size 3451
|