mprzibilla
commited on
Commit
•
2572914
1
Parent(s):
935e974
Training in progress, step 85400
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/optimizer.pt +2 -2
- 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
- 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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db0654f548f6d60f9fd8b399e45b80193a9c3460a41d5fb4ad4343b0d44ce097
|
3 |
+
size 721662341
|
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:e3bfac3added8cfec41660b3a35cd6907e70b7159fe866e0b78e5ddcbba2a65c
|
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 sha256:4d822638689cc8634810d3e1a08b2fa7329b11ee3748f31855aed8bc1092ea8b
|
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:cf62c7d2e834f6c5a166bbc0d23d43228830c679f0bf43523c462fb8cf005e15
|
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 sha256:3db03f7871f85a0ef7adda4d3b586292daaa91f15b19a02e9e95eb8126047dde
|
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,
|
@@ -22,11 +22,27 @@
|
|
22 |
"eval_steps_per_second": 3.376,
|
23 |
"eval_wer": 0.17142857142857143,
|
24 |
"step": 42700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"max_steps": 427000,
|
28 |
"num_train_epochs": 100,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 85400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
22 |
"eval_steps_per_second": 3.376,
|
23 |
"eval_wer": 0.17142857142857143,
|
24 |
"step": 42700
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 20.0,
|
28 |
+
"learning_rate": 8.421915444348577e-05,
|
29 |
+
"loss": 0.198,
|
30 |
+
"step": 85400
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 20.0,
|
34 |
+
"eval_cer": 0.1038961038961039,
|
35 |
+
"eval_loss": 1.091776728630066,
|
36 |
+
"eval_runtime": 7.7941,
|
37 |
+
"eval_samples_per_second": 26.943,
|
38 |
+
"eval_steps_per_second": 3.464,
|
39 |
+
"eval_wer": 0.19523809523809524,
|
40 |
+
"step": 85400
|
41 |
}
|
42 |
],
|
43 |
"max_steps": 427000,
|
44 |
"num_train_epochs": 100,
|
45 |
+
"total_flos": 6.4634027892291396e+19,
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
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:cc93c22e55824b65556a082a61c8a4b4026242b17c39d1296aa07a9ddacd4a52
|
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:e3bfac3added8cfec41660b3a35cd6907e70b7159fe866e0b78e5ddcbba2a65c
|
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:cc93c22e55824b65556a082a61c8a4b4026242b17c39d1296aa07a9ddacd4a52
|
3 |
size 3451
|