codefactory4791
commited on
Commit
•
98af74a
1
Parent(s):
ed31104
Training in progress, step 1500
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 +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 sha256:4d9e68e8a5f341b6ba0ab0b07343bee93a5b63297cde754a4568bb7d4947e3fd
|
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:b43df399cdb010c38bc4ab80c32326c537631ae6d19412ab93238ddd4d643038
|
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 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d0580bfb9cc7cda8f11fa06b89c6cf1894480d400a376db1011a0887a6bd798
|
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 sha256:2d9ae925633048517f97974ea0960ae0d66a4ad50d695096192573be924728a4
|
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:e09503a8cefdc2f864e23d8084344fd955133ac6704435917ca200db3435aae5
|
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,
|
@@ -48,11 +48,32 @@
|
|
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":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 29.558444185928884,
|
3 |
+
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-1500",
|
4 |
+
"epoch": 3.826530612244898,
|
5 |
+
"global_step": 1500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
48 |
"eval_steps_per_second": 0.145,
|
49 |
"eval_wer": 32.163269435031104,
|
50 |
"step": 1000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.19,
|
54 |
+
"learning_rate": 9.215789473684211e-06,
|
55 |
+
"loss": 0.3928,
|
56 |
+
"step": 1250
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.83,
|
60 |
+
"learning_rate": 8.95263157894737e-06,
|
61 |
+
"loss": 0.3263,
|
62 |
+
"step": 1500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.83,
|
66 |
+
"eval_loss": 0.5298507809638977,
|
67 |
+
"eval_runtime": 296.4623,
|
68 |
+
"eval_samples_per_second": 4.652,
|
69 |
+
"eval_steps_per_second": 0.148,
|
70 |
+
"eval_wer": 29.558444185928884,
|
71 |
+
"step": 1500
|
72 |
}
|
73 |
],
|
74 |
"max_steps": 10000,
|
75 |
"num_train_epochs": 26,
|
76 |
+
"total_flos": 2.76652394016768e+19,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|
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:b43df399cdb010c38bc4ab80c32326c537631ae6d19412ab93238ddd4d643038
|
3 |
size 967102601
|