Hugging Face's logo

noflm
/
whisper-base-ja-elite

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
bbd1579
•
1 Parent(s): d0b54d2

Training in progress, step 3000

Browse files
Files changed (11) hide show
  1. checkpoint-3000/config.json +54 -0
  2. checkpoint-3000/optimizer.pt +3 -0
  3. checkpoint-3000/preprocessor_config.json +0 -0
  4. checkpoint-3000/pytorch_model.bin +3 -0
  5. checkpoint-3000/rng_state.pth +3 -0
  6. checkpoint-3000/scaler.pt +3 -0
  7. checkpoint-3000/scheduler.pt +3 -0
  8. checkpoint-3000/trainer_state.json +223 -0
  9. checkpoint-3000/training_args.bin +3 -0
  10. pytorch_model.bin +1 -1
  11. runs/Dec29_11-05-20_srv/events.out.tfevents.1672311942.srv.13534.0 +2 -2
checkpoint-3000/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-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a9a6ba3514ea9d6db1a08bb4a0c88bfb930473d0585e67f9c387a723f5f585
3
+ size 580895237
checkpoint-3000/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff1da28c51d823737fb4818883912c8ef38a3f7deab6ac12f7330b85ce6746d
3
+ size 290458721
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d2f60cb6280cb118cbcd7fdc141e319d16420633e0be7a8e959cbbd5c286a3
3
+ size 14575
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67052f7ccf0c314ec66f8a5e6561069877b7b24a3a43dcf29f3baded513f272d
3
+ size 557
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb034e50379aa6ea99cbc9d658e4acd9811df68b30554db29c35cbfd17ee561
3
+ size 627
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 333.0003,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 11.0,
12
+ "learning_rate": 4.85e-06,
13
+ "loss": 0.716,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 22.0,
18
+ "learning_rate": 9.85e-06,
19
+ "loss": 0.0615,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 33.0,
24
+ "learning_rate": 1e-05,
25
+ "loss": 0.0043,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 44.0,
30
+ "learning_rate": 1e-05,
31
+ "loss": 0.002,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 55.0,
36
+ "learning_rate": 1e-05,
37
+ "loss": 0.0008,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 66.0,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.0006,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 77.0,
48
+ "learning_rate": 1e-05,
49
+ "loss": 0.0004,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 88.0,
54
+ "learning_rate": 1e-05,
55
+ "loss": 0.0003,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 99.0,
60
+ "learning_rate": 1e-05,
61
+ "loss": 0.0003,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 111.0,
66
+ "learning_rate": 1e-05,
67
+ "loss": 0.0002,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 111.0,
72
+ "eval_loss": 0.21552081406116486,
73
+ "eval_runtime": 10.773,
74
+ "eval_samples_per_second": 1.671,
75
+ "eval_steps_per_second": 0.093,
76
+ "eval_wer": 9.75609756097561,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 122.0,
81
+ "learning_rate": 1e-05,
82
+ "loss": 0.0002,
83
+ "step": 1100
84
+ },
85
+ {
86
+ "epoch": 133.0,
87
+ "learning_rate": 1e-05,
88
+ "loss": 0.0002,
89
+ "step": 1200
90
+ },
91
+ {
92
+ "epoch": 144.0,
93
+ "learning_rate": 1e-05,
94
+ "loss": 0.0001,
95
+ "step": 1300
96
+ },
97
+ {
98
+ "epoch": 155.0,
99
+ "learning_rate": 1e-05,
100
+ "loss": 0.0001,
101
+ "step": 1400
102
+ },
103
+ {
104
+ "epoch": 166.0,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.0001,
107
+ "step": 1500
108
+ },
109
+ {
110
+ "epoch": 177.0,
111
+ "learning_rate": 1e-05,
112
+ "loss": 0.0001,
113
+ "step": 1600
114
+ },
115
+ {
116
+ "epoch": 188.0,
117
+ "learning_rate": 1e-05,
118
+ "loss": 0.0001,
119
+ "step": 1700
120
+ },
121
+ {
122
+ "epoch": 199.0,
123
+ "learning_rate": 1e-05,
124
+ "loss": 0.0001,
125
+ "step": 1800
126
+ },
127
+ {
128
+ "epoch": 211.0,
129
+ "learning_rate": 1e-05,
130
+ "loss": 0.0001,
131
+ "step": 1900
132
+ },
133
+ {
134
+ "epoch": 222.0,
135
+ "learning_rate": 1e-05,
136
+ "loss": 0.0001,
137
+ "step": 2000
138
+ },
139
+ {
140
+ "epoch": 222.0,
141
+ "eval_loss": 0.2447899729013443,
142
+ "eval_runtime": 14.1456,
143
+ "eval_samples_per_second": 1.272,
144
+ "eval_steps_per_second": 0.071,
145
+ "eval_wer": 12.195121951219512,
146
+ "step": 2000
147
+ },
148
+ {
149
+ "epoch": 233.0,
150
+ "learning_rate": 1e-05,
151
+ "loss": 0.0001,
152
+ "step": 2100
153
+ },
154
+ {
155
+ "epoch": 244.0,
156
+ "learning_rate": 1e-05,
157
+ "loss": 0.0001,
158
+ "step": 2200
159
+ },
160
+ {
161
+ "epoch": 255.0,
162
+ "learning_rate": 1e-05,
163
+ "loss": 0.0001,
164
+ "step": 2300
165
+ },
166
+ {
167
+ "epoch": 266.0,
168
+ "learning_rate": 1e-05,
169
+ "loss": 0.0001,
170
+ "step": 2400
171
+ },
172
+ {
173
+ "epoch": 277.0,
174
+ "learning_rate": 1e-05,
175
+ "loss": 0.0,
176
+ "step": 2500
177
+ },
178
+ {
179
+ "epoch": 288.0,
180
+ "learning_rate": 1e-05,
181
+ "loss": 0.0,
182
+ "step": 2600
183
+ },
184
+ {
185
+ "epoch": 299.0,
186
+ "learning_rate": 1e-05,
187
+ "loss": 0.0,
188
+ "step": 2700
189
+ },
190
+ {
191
+ "epoch": 311.0,
192
+ "learning_rate": 1e-05,
193
+ "loss": 0.0,
194
+ "step": 2800
195
+ },
196
+ {
197
+ "epoch": 322.0,
198
+ "learning_rate": 1e-05,
199
+ "loss": 0.0,
200
+ "step": 2900
201
+ },
202
+ {
203
+ "epoch": 333.0,
204
+ "learning_rate": 1e-05,
205
+ "loss": 0.0,
206
+ "step": 3000
207
+ },
208
+ {
209
+ "epoch": 333.0,
210
+ "eval_loss": 0.2674005329608917,
211
+ "eval_runtime": 8.0249,
212
+ "eval_samples_per_second": 2.243,
213
+ "eval_steps_per_second": 0.125,
214
+ "eval_wer": 13.414634146341465,
215
+ "step": 3000
216
+ }
217
+ ],
218
+ "max_steps": 10000,
219
+ "num_train_epochs": 9223372036854775807,
220
+ "total_flos": 5.88098557181952e+18,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c36b35e37212c7c09dbca6abb82e5ea958e60ecae5b6ed572ed342d641b50f3
3
+ size 3643
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41743ac18fc5950c53b1ff840c995ec5a357f3cc4970952fee087c9addd50905
3
  size 290458721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff1da28c51d823737fb4818883912c8ef38a3f7deab6ac12f7330b85ce6746d
3
  size 290458721
runs/Dec29_11-05-20_srv/events.out.tfevents.1672311942.srv.13534.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b96c31bd693e2285579df0988e25ac68a155b117c3840ab359950adfc4ea43ce
3
- size 8204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cbbf28149bb7214579e204ce6f59b932c0bdae6db17a9957ee2d1d31711a4b
3
+ size 10092