Commit
•
01b1ab2
1
Parent(s):
62cfe65
Training in progress, step 2500
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 +24 -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 734250209
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:673faac3a07e0a62c11bc11416afef60ddf65d4e550b23bf3f9193eee8c09100
|
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:fef492c0cc91dd26b5baea33552607cd3daad5694a5eec02837d01de1b98ee37
|
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:dedc7b4e2e0881f60071cf978bcc89b7636ec747a7f9e64f1eb4dfbe544bc3ab
|
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:a27e277169a8d74eee3696148b0c8ab773bd8ced4368efa5df115f9ba2083d99
|
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 sha256:61a348781fcdf3b4f98478a89799b0356dc21e6a7fd14b5d7e98066428c9d6b1
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 28.157402255829243,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -90,11 +90,32 @@
|
|
90 |
"eval_steps_per_second": 0.152,
|
91 |
"eval_wer": 28.157402255829243,
|
92 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 10000,
|
96 |
"num_train_epochs": 26,
|
97 |
-
"total_flos":
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 28.157402255829243,
|
3 |
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
+
"epoch": 6.377551020408164,
|
5 |
+
"global_step": 2500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
90 |
"eval_steps_per_second": 0.152,
|
91 |
"eval_wer": 28.157402255829243,
|
92 |
"step": 2000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 5.74,
|
96 |
+
"learning_rate": 8.163157894736842e-06,
|
97 |
+
"loss": 0.1817,
|
98 |
+
"step": 2250
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.38,
|
102 |
+
"learning_rate": 7.9e-06,
|
103 |
+
"loss": 0.1563,
|
104 |
+
"step": 2500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.38,
|
108 |
+
"eval_loss": 0.6200889348983765,
|
109 |
+
"eval_runtime": 297.5485,
|
110 |
+
"eval_samples_per_second": 4.635,
|
111 |
+
"eval_steps_per_second": 0.148,
|
112 |
+
"eval_wer": 39.52253300288301,
|
113 |
+
"step": 2500
|
114 |
}
|
115 |
],
|
116 |
"max_steps": 10000,
|
117 |
"num_train_epochs": 26,
|
118 |
+
"total_flos": 4.60957459931136e+19,
|
119 |
"trial_name": null,
|
120 |
"trial_params": null
|
121 |
}
|
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:fef492c0cc91dd26b5baea33552607cd3daad5694a5eec02837d01de1b98ee37
|
3 |
size 967102601
|