mprzibilla
commited on
Commit
•
30aa651
1
Parent(s):
16a52e5
Training in progress, epoch 15
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 sha256:462ffbbe65d1380f61dfd3f21b5d7c4b86b167a0672adf8d24f2990268ef26c9
|
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:d350923e090f70cd6cb3ca3c24a77877755b996a44d1d18d25f49a34d02f0ea2
|
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 sha256:6bf93ccba67f9be5515023d04a1cc35f1866645ff18209f29735ef048d8305fd
|
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 sha256:555064d5ae7449b6116445d908d550cd6a846dc91eeb271e1e9dcede3b92d71d
|
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 sha256:9378d54f67fa75f090c07a0b880b082c7ac2926177e9eb5704ca2e9e1108531b
|
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,
|
@@ -244,11 +244,28 @@
|
|
244 |
"eval_samples_per_second": 27.489,
|
245 |
"eval_steps_per_second": 3.534,
|
246 |
"step": 59780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
247 |
}
|
248 |
],
|
249 |
"max_steps": 64050,
|
250 |
"num_train_epochs": 15,
|
251 |
-
"total_flos":
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|
254 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 64050,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
244 |
"eval_samples_per_second": 27.489,
|
245 |
"eval_steps_per_second": 3.534,
|
246 |
"step": 59780
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 15.0,
|
250 |
+
"learning_rate": 4.7659742308703654e-08,
|
251 |
+
"loss": 0.0409,
|
252 |
+
"step": 64050
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 15.0,
|
256 |
+
"eval_cer": 0.09264069264069263,
|
257 |
+
"eval_loss": 1.0212522745132446,
|
258 |
+
"eval_new_wer": 0.1,
|
259 |
+
"eval_old_wer": 0.1380952380952381,
|
260 |
+
"eval_runtime": 7.658,
|
261 |
+
"eval_samples_per_second": 27.422,
|
262 |
+
"eval_steps_per_second": 3.526,
|
263 |
+
"step": 64050
|
264 |
}
|
265 |
],
|
266 |
"max_steps": 64050,
|
267 |
"num_train_epochs": 15,
|
268 |
+
"total_flos": 5.079400634281409e+19,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|
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:d350923e090f70cd6cb3ca3c24a77877755b996a44d1d18d25f49a34d02f0ea2
|
3 |
size 377646433
|