mprzibilla
commited on
Commit
•
af77d5d
1
Parent(s):
25baf52
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 +1 -1
- 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 sha256:3708f0232add0b440707331fbfc234ae93e774e96ceb137682e09c3db9f76cc4
|
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 sha256:143df86c3f9bb95948dbe505f344eafcf3df2e17b8ab7775170f907fe290411d
|
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 14639
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37826454889cc005af1c4a5ffcdd7fcc45d5f29df3e5ea3ad78cccc90d3f06fb
|
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:f0ff467205290e05f676b0bf254ddb940e84b6639dc95eeadff858daeeb3c5af
|
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 sha256:8c0bc953e7af64bbf30cf0c251471e6877e9e05200f974ad209e3be5f909477b
|
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": 23.57,
|
228 |
"eval_steps_per_second": 3.03,
|
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": 23.57,
|
228 |
"eval_steps_per_second": 3.03,
|
229 |
"step": 55510
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 14.0,
|
233 |
+
"learning_rate": 7.065145937417829e-06,
|
234 |
+
"loss": 0.0337,
|
235 |
+
"step": 59780
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 14.0,
|
239 |
+
"eval_cer": 0.6138528138528139,
|
240 |
+
"eval_loss": 4.218883514404297,
|
241 |
+
"eval_new_wer": 0.30952380952380953,
|
242 |
+
"eval_old_wer": 1.0,
|
243 |
+
"eval_runtime": 8.8331,
|
244 |
+
"eval_samples_per_second": 23.774,
|
245 |
+
"eval_steps_per_second": 3.057,
|
246 |
+
"step": 59780
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 64050,
|
250 |
"num_train_epochs": 15,
|
251 |
+
"total_flos": 4.7376645895196344e+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 sha256:143df86c3f9bb95948dbe505f344eafcf3df2e17b8ab7775170f907fe290411d
|
3 |
size 377646433
|