Hugging Face's logo

rocky250
/
ASR_Extend

Safetensors
whisper
Model card Files
xet
 Community
rocky250 commited on
Commit
c86eaa9
·
verified ·
1 Parent(s): a5db44b

Upload full training state for checkpoint-4000

Browse files
Files changed (9) hide show
  1. checkpoint-4000/config.json +65 -0
  2. checkpoint-4000/generation_config.json +264 -0
  3. checkpoint-4000/model.safetensors +3 -0
  4. checkpoint-4000/optimizer.pt +3 -0
  5. checkpoint-4000/preprocessor_config.json +14 -0
  6. checkpoint-4000/rng_state.pth +3 -0
  7. checkpoint-4000/scheduler.pt +3 -0
  8. checkpoint-4000/trainer_state.json +261 -0
  9. checkpoint-4000/training_args.bin +3 -0
checkpoint-4000/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rocky250/ASR_Extend",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50302
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 12,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [],
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.36.2",
62
+ "use_cache": false,
63
+ "use_weighted_layer_sum": false,
64
+ "vocab_size": 51865
65
+ }
checkpoint-4000/generation_config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 50,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "prev_sot_token_id": 50361,
168
+ "return_timestamps": false,
169
+ "suppress_tokens": [
170
+ 1,
171
+ 2,
172
+ 7,
173
+ 8,
174
+ 9,
175
+ 10,
176
+ 14,
177
+ 25,
178
+ 26,
179
+ 27,
180
+ 28,
181
+ 29,
182
+ 31,
183
+ 58,
184
+ 59,
185
+ 60,
186
+ 61,
187
+ 62,
188
+ 63,
189
+ 90,
190
+ 91,
191
+ 92,
192
+ 93,
193
+ 359,
194
+ 503,
195
+ 522,
196
+ 542,
197
+ 873,
198
+ 893,
199
+ 902,
200
+ 918,
201
+ 922,
202
+ 931,
203
+ 1350,
204
+ 1853,
205
+ 1982,
206
+ 2460,
207
+ 2627,
208
+ 3246,
209
+ 3253,
210
+ 3268,
211
+ 3536,
212
+ 3846,
213
+ 3961,
214
+ 4183,
215
+ 4667,
216
+ 6585,
217
+ 6647,
218
+ 7273,
219
+ 9061,
220
+ 9383,
221
+ 10428,
222
+ 10929,
223
+ 11938,
224
+ 12033,
225
+ 12331,
226
+ 12562,
227
+ 13793,
228
+ 14157,
229
+ 14635,
230
+ 15265,
231
+ 15618,
232
+ 16553,
233
+ 16604,
234
+ 18362,
235
+ 18956,
236
+ 20075,
237
+ 21675,
238
+ 22520,
239
+ 26130,
240
+ 26161,
241
+ 26435,
242
+ 28279,
243
+ 29464,
244
+ 31650,
245
+ 32302,
246
+ 32470,
247
+ 36865,
248
+ 42863,
249
+ 47425,
250
+ 49870,
251
+ 50254,
252
+ 50258,
253
+ 50358,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362
258
+ ],
259
+ "task_to_id": {
260
+ "transcribe": 50359,
261
+ "translate": 50358
262
+ },
263
+ "transformers_version": "4.36.2"
264
+ }
checkpoint-4000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0247e968449e99a69baf759be65c61ae964df994c4e861a64f0985f6c3615b4b
3
+ size 966995080
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bee9b2262f3d938e17e8bf7b3ab3627f26fd1561f02659cc2613e3d312d442
3
+ size 1925064509
checkpoint-4000/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d18c5b20f76ed4814de75a7b3f813c9cd2fc5b24b1eeac247880b6bd8ee67a0
3
+ size 14645
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172ebd0c303fc63bf85830bf9c1a7c81922caeda8f667b15bc032cd0bcf0edad
3
+ size 1465
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0120481927710845,
5
+ "eval_steps": 500,
6
+ "global_step": 4000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 5.000000000000001e-07,
14
+ "loss": 0.2303,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.15,
19
+ "learning_rate": 1.0000000000000002e-06,
20
+ "loss": 0.21,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 0.23,
25
+ "learning_rate": 1.5e-06,
26
+ "loss": 0.2118,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 0.3,
31
+ "learning_rate": 2.0000000000000003e-06,
32
+ "loss": 0.2131,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 0.38,
37
+ "learning_rate": 2.5e-06,
38
+ "loss": 0.2076,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 0.45,
43
+ "learning_rate": 3e-06,
44
+ "loss": 0.2116,
45
+ "step": 600
46
+ },
47
+ {
48
+ "epoch": 0.53,
49
+ "learning_rate": 3.5e-06,
50
+ "loss": 0.2154,
51
+ "step": 700
52
+ },
53
+ {
54
+ "epoch": 0.6,
55
+ "learning_rate": 4.000000000000001e-06,
56
+ "loss": 0.2129,
57
+ "step": 800
58
+ },
59
+ {
60
+ "epoch": 0.68,
61
+ "learning_rate": 4.5e-06,
62
+ "loss": 0.211,
63
+ "step": 900
64
+ },
65
+ {
66
+ "epoch": 0.75,
67
+ "learning_rate": 5e-06,
68
+ "loss": 0.2178,
69
+ "step": 1000
70
+ },
71
+ {
72
+ "epoch": 0.83,
73
+ "learning_rate": 5.500000000000001e-06,
74
+ "loss": 0.2104,
75
+ "step": 1100
76
+ },
77
+ {
78
+ "epoch": 0.9,
79
+ "learning_rate": 6e-06,
80
+ "loss": 0.215,
81
+ "step": 1200
82
+ },
83
+ {
84
+ "epoch": 0.98,
85
+ "learning_rate": 6.5000000000000004e-06,
86
+ "loss": 0.2107,
87
+ "step": 1300
88
+ },
89
+ {
90
+ "epoch": 1.05,
91
+ "learning_rate": 7e-06,
92
+ "loss": 0.2091,
93
+ "step": 1400
94
+ },
95
+ {
96
+ "epoch": 1.13,
97
+ "learning_rate": 7.500000000000001e-06,
98
+ "loss": 0.207,
99
+ "step": 1500
100
+ },
101
+ {
102
+ "epoch": 1.2,
103
+ "learning_rate": 8.000000000000001e-06,
104
+ "loss": 0.1942,
105
+ "step": 1600
106
+ },
107
+ {
108
+ "epoch": 1.28,
109
+ "learning_rate": 8.5e-06,
110
+ "loss": 0.2037,
111
+ "step": 1700
112
+ },
113
+ {
114
+ "epoch": 1.36,
115
+ "learning_rate": 9e-06,
116
+ "loss": 0.2071,
117
+ "step": 1800
118
+ },
119
+ {
120
+ "epoch": 1.43,
121
+ "learning_rate": 9.5e-06,
122
+ "loss": 0.2072,
123
+ "step": 1900
124
+ },
125
+ {
126
+ "epoch": 1.51,
127
+ "learning_rate": 1e-05,
128
+ "loss": 0.2035,
129
+ "step": 2000
130
+ },
131
+ {
132
+ "epoch": 1.58,
133
+ "learning_rate": 9.666666666666667e-06,
134
+ "loss": 0.21,
135
+ "step": 2100
136
+ },
137
+ {
138
+ "epoch": 1.66,
139
+ "learning_rate": 9.333333333333334e-06,
140
+ "loss": 0.2062,
141
+ "step": 2200
142
+ },
143
+ {
144
+ "epoch": 1.73,
145
+ "learning_rate": 9e-06,
146
+ "loss": 0.2067,
147
+ "step": 2300
148
+ },
149
+ {
150
+ "epoch": 1.81,
151
+ "learning_rate": 8.666666666666668e-06,
152
+ "loss": 0.2043,
153
+ "step": 2400
154
+ },
155
+ {
156
+ "epoch": 1.88,
157
+ "learning_rate": 8.333333333333334e-06,
158
+ "loss": 0.1953,
159
+ "step": 2500
160
+ },
161
+ {
162
+ "epoch": 1.96,
163
+ "learning_rate": 8.000000000000001e-06,
164
+ "loss": 0.2021,
165
+ "step": 2600
166
+ },
167
+ {
168
+ "epoch": 2.03,
169
+ "learning_rate": 7.666666666666667e-06,
170
+ "loss": 0.1764,
171
+ "step": 2700
172
+ },
173
+ {
174
+ "epoch": 2.11,
175
+ "learning_rate": 7.333333333333333e-06,
176
+ "loss": 0.1506,
177
+ "step": 2800
178
+ },
179
+ {
180
+ "epoch": 2.18,
181
+ "learning_rate": 7e-06,
182
+ "loss": 0.152,
183
+ "step": 2900
184
+ },
185
+ {
186
+ "epoch": 2.26,
187
+ "learning_rate": 6.666666666666667e-06,
188
+ "loss": 0.1539,
189
+ "step": 3000
190
+ },
191
+ {
192
+ "epoch": 2.33,
193
+ "learning_rate": 6.333333333333333e-06,
194
+ "loss": 0.1509,
195
+ "step": 3100
196
+ },
197
+ {
198
+ "epoch": 2.41,
199
+ "learning_rate": 6e-06,
200
+ "loss": 0.1504,
201
+ "step": 3200
202
+ },
203
+ {
204
+ "epoch": 2.48,
205
+ "learning_rate": 5.666666666666667e-06,
206
+ "loss": 0.1484,
207
+ "step": 3300
208
+ },
209
+ {
210
+ "epoch": 2.56,
211
+ "learning_rate": 5.333333333333334e-06,
212
+ "loss": 0.1501,
213
+ "step": 3400
214
+ },
215
+ {
216
+ "epoch": 2.64,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.1479,
219
+ "step": 3500
220
+ },
221
+ {
222
+ "epoch": 2.71,
223
+ "learning_rate": 4.666666666666667e-06,
224
+ "loss": 0.1489,
225
+ "step": 3600
226
+ },
227
+ {
228
+ "epoch": 2.79,
229
+ "learning_rate": 4.333333333333334e-06,
230
+ "loss": 0.1494,
231
+ "step": 3700
232
+ },
233
+ {
234
+ "epoch": 2.86,
235
+ "learning_rate": 4.000000000000001e-06,
236
+ "loss": 0.1481,
237
+ "step": 3800
238
+ },
239
+ {
240
+ "epoch": 2.94,
241
+ "learning_rate": 3.6666666666666666e-06,
242
+ "loss": 0.1478,
243
+ "step": 3900
244
+ },
245
+ {
246
+ "epoch": 3.01,
247
+ "learning_rate": 3.3333333333333333e-06,
248
+ "loss": 0.1355,
249
+ "step": 4000
250
+ }
251
+ ],
252
+ "logging_steps": 100,
253
+ "max_steps": 5000,
254
+ "num_input_tokens_seen": 0,
255
+ "num_train_epochs": 4,
256
+ "save_steps": 1000,
257
+ "total_flos": 9.23386705403904e+18,
258
+ "train_batch_size": 4,
259
+ "trial_name": null,
260
+ "trial_params": null
261
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330222e9d1dbca68c3829d13bc0f3ef3374975e99afc1eda59381f6f34285201
3
+ size 5265