codefactory4791
commited on
Commit
•
62cfe65
1
Parent(s):
98af74a
Training in progress, step 2000
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 sha256:6e0b18b0ccfcf731a02b69f49d84a41ffb907067b96804841d9716574f1d8987
|
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:d74cc79ce25091fc0d7152a90f2b61e9c8b813c2ca9ad8b92b2c9254f86464cc
|
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:c76046ce08fc2ad2ab65ff777d8d964f3f0d1687174751d5f5f91bfa6f58312e
|
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 sha256:84fbd27040a19de357ace099cb5b9d07e88f2d526ee1a3b6e71423294ac09303
|
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 sha256:3faccf62edccc3658ae48d94489077608d30a053c6f565f916d741d2b667ee62
|
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,
|
@@ -69,11 +69,32 @@
|
|
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":
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 28.157402255829243,
|
3 |
+
"best_model_checkpoint": "codefactory4791/whisper-small-medicalv2/checkpoint-2000",
|
4 |
+
"epoch": 5.1020408163265305,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
69 |
"eval_steps_per_second": 0.148,
|
70 |
"eval_wer": 29.558444185928884,
|
71 |
"step": 1500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.46,
|
75 |
+
"learning_rate": 8.689473684210526e-06,
|
76 |
+
"loss": 0.2629,
|
77 |
+
"step": 1750
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 5.1,
|
81 |
+
"learning_rate": 8.426315789473684e-06,
|
82 |
+
"loss": 0.2399,
|
83 |
+
"step": 2000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 5.1,
|
87 |
+
"eval_loss": 0.5742943286895752,
|
88 |
+
"eval_runtime": 290.0311,
|
89 |
+
"eval_samples_per_second": 4.755,
|
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": 3.6873999525888e+19,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
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:d74cc79ce25091fc0d7152a90f2b61e9c8b813c2ca9ad8b92b2c9254f86464cc
|
3 |
size 967102601
|