codefactory4791
commited on
Commit
•
ed31104
1
Parent(s):
e0a536e
Training in progress, step 1000
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 +26 -5
- 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 734250209
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d434f985c9d09b6feed58213b3a8c540ef1cdc1da6cbbd80edf9bea452377a8d
|
3 |
size 734250209
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bc0d57f24aa0969a5cd7d12fe71c59b164f911024bc91c51a4f1be3363ece6
|
3 |
size 967102601
|
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:a0b67205a01f81cbfed31ef9c8d88b8ca9fb2b7c63c8fc89bb70ceddaf264935
|
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:ea7b30d18246e9f199d23f32266d32c441d1d76efd3d77861aca564f1f1740f2
|
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 sha256:95995652e2201d022bab8bd2b36dc249a93959b19ec015fedbe94c1bbb6cdd79
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -27,11 +27,32 @@
|
|
27 |
"eval_steps_per_second": 0.135,
|
28 |
"eval_wer": 46.628900915482276,
|
29 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|
31 |
],
|
32 |
"max_steps": 10000,
|
33 |
"num_train_epochs": 26,
|
34 |
-
"total_flos":
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 32.163269435031104,
|
3 |
+
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-1000",
|
4 |
+
"epoch": 2.5510204081632653,
|
5 |
+
"global_step": 1000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
27 |
"eval_steps_per_second": 0.135,
|
28 |
"eval_wer": 46.628900915482276,
|
29 |
"step": 500
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.91,
|
33 |
+
"learning_rate": 9.742105263157897e-06,
|
34 |
+
"loss": 0.5005,
|
35 |
+
"step": 750
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.55,
|
39 |
+
"learning_rate": 9.478947368421053e-06,
|
40 |
+
"loss": 0.4125,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.55,
|
45 |
+
"eval_loss": 0.5011524558067322,
|
46 |
+
"eval_runtime": 303.4033,
|
47 |
+
"eval_samples_per_second": 4.545,
|
48 |
+
"eval_steps_per_second": 0.145,
|
49 |
+
"eval_wer": 32.163269435031104,
|
50 |
+
"step": 1000
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 10000,
|
54 |
"num_train_epochs": 26,
|
55 |
+
"total_flos": 1.84434929344512e+19,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8bc0d57f24aa0969a5cd7d12fe71c59b164f911024bc91c51a4f1be3363ece6
|
3 |
size 967102601
|