mprzibilla
commited on
Commit
•
1428a81
1
Parent(s):
3cbdecf
Training in progress, epoch 14
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 sha256:02c3032c97cfb406e3df1997fc82b235fdf4b343d9731893321aff309d3ec39b
|
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:e03198156019d4a4cc89c394475471f08334d5aa6d515bea3d95adfd769ee04d
|
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 sha256:4b582a61fc9db0b4c3ab7f9c6bcc7ec92bd6b554c9167e6aaf8ccf981d726604
|
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 sha256:812ba51647b28422373531c50c6c75a733798cf99f711de0c49157a2c51b5905
|
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 sha256:9e23e7308fe04ea4571d59a06bafc7864cde86f32c2c2dfcbb4d0fa8be4a954b
|
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,
|
@@ -227,11 +227,28 @@
|
|
227 |
"eval_samples_per_second": 24.743,
|
228 |
"eval_steps_per_second": 3.181,
|
229 |
"step": 55510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
}
|
231 |
],
|
232 |
"max_steps": 64050,
|
233 |
"num_train_epochs": 15,
|
234 |
-
"total_flos": 4.
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 14.0,
|
5 |
+
"global_step": 59780,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
227 |
"eval_samples_per_second": 24.743,
|
228 |
"eval_steps_per_second": 3.181,
|
229 |
"step": 55510
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 14.0,
|
233 |
+
"learning_rate": 7.063502498027873e-06,
|
234 |
+
"loss": 0.0573,
|
235 |
+
"step": 59780
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 14.0,
|
239 |
+
"eval_cer": 0.09177489177489177,
|
240 |
+
"eval_loss": 0.5790263414382935,
|
241 |
+
"eval_new_wer": 0.10952380952380952,
|
242 |
+
"eval_old_wer": 0.14285714285714285,
|
243 |
+
"eval_runtime": 8.6001,
|
244 |
+
"eval_samples_per_second": 24.418,
|
245 |
+
"eval_steps_per_second": 3.139,
|
246 |
+
"step": 59780
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 64050,
|
250 |
"num_train_epochs": 15,
|
251 |
+
"total_flos": 4.529033204206461e+19,
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
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:e03198156019d4a4cc89c394475471f08334d5aa6d515bea3d95adfd769ee04d
|
3 |
size 377646433
|