Hugging Face's logo

noflm
/
whisper-base-ja-cv11

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Japanese
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
noflm commited on
Commit
5711a1b
•
1 Parent(s): e5adfed

Training in progress, step 6000

Browse files
Files changed (11) hide show
  1. checkpoint-6000/config.json +54 -0
  2. checkpoint-6000/optimizer.pt +3 -0
  3. checkpoint-6000/preprocessor_config.json +0 -0
  4. checkpoint-6000/pytorch_model.bin +3 -0
  5. checkpoint-6000/rng_state.pth +3 -0
  6. checkpoint-6000/scaler.pt +3 -0
  7. checkpoint-6000/scheduler.pt +3 -0
  8. checkpoint-6000/trainer_state.json +142 -0
  9. checkpoint-6000/training_args.bin +3 -0
  10. pytorch_model.bin +1 -1
  11. runs/Dec27_09-55-14_srv/events.out.tfevents.1672134971.srv.1172111.0 +2 -2
checkpoint-6000/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-base",
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": 512,
15
+ "decoder_attention_heads": 8,
16
+ "decoder_ffn_dim": 2048,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 8,
22
+ "encoder_ffn_dim": 2048,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": [
27
+ [
28
+ 1,
29
+ 50266
30
+ ],
31
+ [
32
+ 2,
33
+ 50359
34
+ ],
35
+ [
36
+ 3,
37
+ 50363
38
+ ]
39
+ ],
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "max_length": 448,
43
+ "max_source_positions": 1500,
44
+ "max_target_positions": 448,
45
+ "model_type": "whisper",
46
+ "num_hidden_layers": 6,
47
+ "num_mel_bins": 80,
48
+ "pad_token_id": 50257,
49
+ "scale_embedding": false,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.26.0.dev0",
52
+ "use_cache": false,
53
+ "vocab_size": 51865
54
+ }
checkpoint-6000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c5a0626785c0debb6ddfbcd36bc7a0fea5d54a09ce1b2d0c3dedd5bef60701
3
+ size 580895237
checkpoint-6000/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff5d55ffb58ba69788c13c21edcf98b2158bc180aa8d52fb1d178b0a4660917
3
+ size 290458721
checkpoint-6000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698b14e1b708f4a032c3ce1f94ca451d6fb682775083b990ff715f60f2e96425
3
+ size 14639
checkpoint-6000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ea19f5486303e6d646e2340cbed42938aa061a643312912899a9ba49e1316e
3
+ size 557
checkpoint-6000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281fc35f43ffe588e10035f1ab62d6cfb90b508eba0189f31a33cebc6e1233ab
3
+ size 627
checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 21.0099,
5
+ "global_step": 6000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.02,
12
+ "learning_rate": 9.960000000000001e-06,
13
+ "loss": 0.5615,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.02,
18
+ "learning_rate": 1e-05,
19
+ "loss": 0.3273,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 3.02,
24
+ "eval_loss": 0.4225325584411621,
25
+ "eval_runtime": 1489.9228,
26
+ "eval_samples_per_second": 3.09,
27
+ "eval_steps_per_second": 0.193,
28
+ "eval_wer": 20.82533081951615,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 5.01,
33
+ "learning_rate": 1e-05,
34
+ "loss": 0.1859,
35
+ "step": 1500
36
+ },
37
+ {
38
+ "epoch": 7.0,
39
+ "learning_rate": 1e-05,
40
+ "loss": 0.0923,
41
+ "step": 2000
42
+ },
43
+ {
44
+ "epoch": 7.0,
45
+ "eval_loss": 0.46434369683265686,
46
+ "eval_runtime": 1504.5618,
47
+ "eval_samples_per_second": 3.06,
48
+ "eval_steps_per_second": 0.191,
49
+ "eval_wer": 21.22002361108664,
50
+ "step": 2000
51
+ },
52
+ {
53
+ "epoch": 8.03,
54
+ "learning_rate": 1e-05,
55
+ "loss": 0.0369,
56
+ "step": 2500
57
+ },
58
+ {
59
+ "epoch": 10.02,
60
+ "learning_rate": 1e-05,
61
+ "loss": 0.0164,
62
+ "step": 3000
63
+ },
64
+ {
65
+ "epoch": 10.02,
66
+ "eval_loss": 0.5403426885604858,
67
+ "eval_runtime": 1504.7378,
68
+ "eval_samples_per_second": 3.06,
69
+ "eval_steps_per_second": 0.191,
70
+ "eval_wer": 22.962662766725987,
71
+ "step": 3000
72
+ },
73
+ {
74
+ "epoch": 12.01,
75
+ "learning_rate": 1e-05,
76
+ "loss": 0.0089,
77
+ "step": 3500
78
+ },
79
+ {
80
+ "epoch": 14.01,
81
+ "learning_rate": 1e-05,
82
+ "loss": 0.006,
83
+ "step": 4000
84
+ },
85
+ {
86
+ "epoch": 14.01,
87
+ "eval_loss": 0.5819889307022095,
88
+ "eval_runtime": 1478.853,
89
+ "eval_samples_per_second": 3.113,
90
+ "eval_steps_per_second": 0.195,
91
+ "eval_wer": 21.086109985375224,
92
+ "step": 4000
93
+ },
94
+ {
95
+ "epoch": 16.0,
96
+ "learning_rate": 1e-05,
97
+ "loss": 0.0057,
98
+ "step": 4500
99
+ },
100
+ {
101
+ "epoch": 17.02,
102
+ "learning_rate": 1e-05,
103
+ "loss": 0.0046,
104
+ "step": 5000
105
+ },
106
+ {
107
+ "epoch": 17.02,
108
+ "eval_loss": 0.5851565003395081,
109
+ "eval_runtime": 1532.3442,
110
+ "eval_samples_per_second": 3.005,
111
+ "eval_steps_per_second": 0.188,
112
+ "eval_wer": 22.072841964301446,
113
+ "step": 5000
114
+ },
115
+ {
116
+ "epoch": 19.02,
117
+ "learning_rate": 1e-05,
118
+ "loss": 0.0042,
119
+ "step": 5500
120
+ },
121
+ {
122
+ "epoch": 21.01,
123
+ "learning_rate": 1e-05,
124
+ "loss": 0.0034,
125
+ "step": 6000
126
+ },
127
+ {
128
+ "epoch": 21.01,
129
+ "eval_loss": 0.6112661361694336,
130
+ "eval_runtime": 1497.7325,
131
+ "eval_samples_per_second": 3.074,
132
+ "eval_steps_per_second": 0.192,
133
+ "eval_wer": 21.6622909802125,
134
+ "step": 6000
135
+ }
136
+ ],
137
+ "max_steps": 10000,
138
+ "num_train_epochs": 9223372036854775807,
139
+ "total_flos": 1.242315394449408e+19,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
checkpoint-6000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63250d2e981e0cfad1a5508019d2b4e5ef4e64d9d02e786f5ee65312228c5eb2
3
+ size 3643
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a200316dd456070fc2433a73530252da7cda1d5c6c1752891f474252c07d64e
3
  size 290458721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff5d55ffb58ba69788c13c21edcf98b2158bc180aa8d52fb1d178b0a4660917
3
  size 290458721
runs/Dec27_09-55-14_srv/events.out.tfevents.1672134971.srv.1172111.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e14d0f45abec490706428810c4dec039b891475ad7d2e90ad1054a6e51a109c0
3
- size 7588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8837b7467b8ff4379137ba4a9f11209e2cb5102affd4c177296c4f39473deff
3
+ size 8220