mprzibilla
commited on
Commit
•
fb2e773
1
Parent(s):
23f97d6
Training in progress, step 134000
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 +19 -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 174303
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bbc0864acfd13b716f75d307bf48aada3819f622ff0bd60c9128105ebfcff8e
|
3 |
size 174303
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:887961831a0f30b4269cdd28f6acde7f7d51f9a06abaabe2de32501df0b1860f
|
3 |
size 377644503
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93198e96e3eab53a5e609a281fb99228f51dc43ea5bfb0348b2d825a7a3ab647
|
3 |
size 14567
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61823d7f75e62090d2b8f678678ba83a75ec4c530252db1f2a051fa6494b9b82
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26fc2b87137deb440e0add509cb5c6eaf84f92619ce4a6bab36eea0195aa5885
|
3 |
size 623
|
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,
|
@@ -150,11 +150,27 @@
|
|
150 |
"eval_steps_per_second": 27.275,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 120600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 134000,
|
156 |
"num_train_epochs": 250,
|
157 |
-
"total_flos": 1.
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 250.0,
|
5 |
+
"global_step": 134000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_steps_per_second": 27.275,
|
151 |
"eval_wer": 1.0,
|
152 |
"step": 120600
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 250.0,
|
156 |
+
"learning_rate": 4.4776119402985075e-08,
|
157 |
+
"loss": 2.4161,
|
158 |
+
"step": 134000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 250.0,
|
162 |
+
"eval_cer": 0.898989898989899,
|
163 |
+
"eval_loss": 3.1552622318267822,
|
164 |
+
"eval_runtime": 0.843,
|
165 |
+
"eval_samples_per_second": 213.521,
|
166 |
+
"eval_steps_per_second": 27.283,
|
167 |
+
"eval_wer": 1.0,
|
168 |
+
"step": 134000
|
169 |
}
|
170 |
],
|
171 |
"max_steps": 134000,
|
172 |
"num_train_epochs": 250,
|
173 |
+
"total_flos": 1.2448746848771059e+20,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
176 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377644503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:887961831a0f30b4269cdd28f6acde7f7d51f9a06abaabe2de32501df0b1860f
|
3 |
size 377644503
|