Hugging Face's logo

ayberkuckun
/
whisper-small-se-hyperparameter-searched

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ayberkuckun commited on
Commit
d683cfa
•
1 Parent(s): f71375b

Training in progress, step 1000

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. config.json +42 -0
  3. last-checkpoint/config.json +42 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/preprocessor_config.json +0 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scaler.pt +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/trainer_state.json +85 -0
  11. last-checkpoint/training_args.bin +3 -0
  12. preprocessor_config.json +0 -0
  13. pytorch_model.bin +3 -0
  14. runs/Dec09_00-00-42_c3f4f531cb03/1670544089.1981144/events.out.tfevents.1670544089.c3f4f531cb03.77.1 +3 -0
  15. runs/Dec09_00-00-42_c3f4f531cb03/events.out.tfevents.1670544089.c3f4f531cb03.77.0 +3 -0
  16. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 12,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "suppress_tokens": [],
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.26.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": null,
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "max_length": 448,
30
+ "max_source_positions": 1500,
31
+ "max_target_positions": 448,
32
+ "model_type": "whisper",
33
+ "num_hidden_layers": 12,
34
+ "num_mel_bins": 80,
35
+ "pad_token_id": 50257,
36
+ "scale_embedding": false,
37
+ "suppress_tokens": [],
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.26.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 51865
42
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487047e52874981cd1979c337b862003cd35967ac6c8df26a2637ccaaab4125d
3
+ size 1934161093
last-checkpoint/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7106946ffb61d685fbde3e04a6cfae03439996cd64d41641eaf3819896fc1005
3
+ size 967102601
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99577ec182c7cefdfd497c476faa654496184ebc0388b69cd86aa8e5aa1fb90
3
+ size 14511
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc21ee2b74a43540f5e647810d7ac3e1c1d2565032e94208402bd065e4438d5b
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8c931aaa6d4912dc97c7bf803a49fe476094231a21fa92932d4adb4df7af4e
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 21.384205856255544,
3
+ "best_model_checkpoint": "whisper-small-se/checkpoint-1000",
4
+ "epoch": 1.2951456310679612,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.13,
12
+ "learning_rate": 9.699999999999999e-06,
13
+ "loss": 1.9865,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.26,
18
+ "learning_rate": 1.461891891891892e-05,
19
+ "loss": 0.4288,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.39,
24
+ "learning_rate": 1.3808108108108109e-05,
25
+ "loss": 0.3436,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.52,
30
+ "learning_rate": 1.2997297297297297e-05,
31
+ "loss": 0.3151,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.65,
36
+ "learning_rate": 1.2186486486486488e-05,
37
+ "loss": 0.3024,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.78,
42
+ "learning_rate": 1.1375675675675677e-05,
43
+ "loss": 0.2773,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.91,
48
+ "learning_rate": 1.0564864864864865e-05,
49
+ "loss": 0.2901,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 1.04,
54
+ "learning_rate": 9.754054054054054e-06,
55
+ "loss": 0.2207,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 1.17,
60
+ "learning_rate": 8.943243243243243e-06,
61
+ "loss": 0.105,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 1.3,
66
+ "learning_rate": 8.132432432432433e-06,
67
+ "loss": 0.1047,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 1.3,
72
+ "eval_loss": 0.29004809260368347,
73
+ "eval_runtime": 1987.1641,
74
+ "eval_samples_per_second": 2.551,
75
+ "eval_steps_per_second": 0.319,
76
+ "eval_wer": 21.384205856255544,
77
+ "step": 1000
78
+ }
79
+ ],
80
+ "max_steps": 2000,
81
+ "num_train_epochs": 3,
82
+ "total_flos": 4.61967508832256e+18,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d849f919f8a76af705ac736e036cf47f6d926a4424246cc4fc6c30240fe0bdb0
3
+ size 3643
preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7106946ffb61d685fbde3e04a6cfae03439996cd64d41641eaf3819896fc1005
3
+ size 967102601
runs/Dec09_00-00-42_c3f4f531cb03/1670544089.1981144/events.out.tfevents.1670544089.c3f4f531cb03.77.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4481110e6769322206f18a544cf23e2d876ef7fbdbab5fdcd461cbb991034691
3
+ size 5905
runs/Dec09_00-00-42_c3f4f531cb03/events.out.tfevents.1670544089.c3f4f531cb03.77.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224a9506653b73c5ef93ee4811101a42cd4a4a551bb8bcb5bb2da65bcc1df7ce
3
+ size 6214
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d849f919f8a76af705ac736e036cf47f6d926a4424246cc4fc6c30240fe0bdb0
3
+ size 3643