lyhourt commited on
Commit
c2b58ee
1 Parent(s): f9109a6

Training in progress, step 300, checkpoint

Browse files
checkpoint-300/config.json ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lyhourt/whisper-small-custom-3000",
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
+ 50259
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
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50360,
144
+ 50361,
145
+ 50362
146
+ ],
147
+ "torch_dtype": "float32",
148
+ "transformers_version": "4.41.0",
149
+ "use_cache": true,
150
+ "use_weighted_layer_sum": false,
151
+ "vocab_size": 51865
152
+ }
checkpoint-300/generation_config.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_multilingual": true,
52
+ "lang_to_id": {
53
+ "<|af|>": 50327,
54
+ "<|am|>": 50334,
55
+ "<|ar|>": 50272,
56
+ "<|as|>": 50350,
57
+ "<|az|>": 50304,
58
+ "<|ba|>": 50355,
59
+ "<|be|>": 50330,
60
+ "<|bg|>": 50292,
61
+ "<|bn|>": 50302,
62
+ "<|bo|>": 50347,
63
+ "<|br|>": 50309,
64
+ "<|bs|>": 50315,
65
+ "<|ca|>": 50270,
66
+ "<|cs|>": 50283,
67
+ "<|cy|>": 50297,
68
+ "<|da|>": 50285,
69
+ "<|de|>": 50261,
70
+ "<|el|>": 50281,
71
+ "<|en|>": 50259,
72
+ "<|es|>": 50262,
73
+ "<|et|>": 50307,
74
+ "<|eu|>": 50310,
75
+ "<|fa|>": 50300,
76
+ "<|fi|>": 50277,
77
+ "<|fo|>": 50338,
78
+ "<|fr|>": 50265,
79
+ "<|gl|>": 50319,
80
+ "<|gu|>": 50333,
81
+ "<|haw|>": 50352,
82
+ "<|ha|>": 50354,
83
+ "<|he|>": 50279,
84
+ "<|hi|>": 50276,
85
+ "<|hr|>": 50291,
86
+ "<|ht|>": 50339,
87
+ "<|hu|>": 50286,
88
+ "<|hy|>": 50312,
89
+ "<|id|>": 50275,
90
+ "<|is|>": 50311,
91
+ "<|it|>": 50274,
92
+ "<|ja|>": 50266,
93
+ "<|jw|>": 50356,
94
+ "<|ka|>": 50329,
95
+ "<|kk|>": 50316,
96
+ "<|km|>": 50323,
97
+ "<|kn|>": 50306,
98
+ "<|ko|>": 50264,
99
+ "<|la|>": 50294,
100
+ "<|lb|>": 50345,
101
+ "<|ln|>": 50353,
102
+ "<|lo|>": 50336,
103
+ "<|lt|>": 50293,
104
+ "<|lv|>": 50301,
105
+ "<|mg|>": 50349,
106
+ "<|mi|>": 50295,
107
+ "<|mk|>": 50308,
108
+ "<|ml|>": 50296,
109
+ "<|mn|>": 50314,
110
+ "<|mr|>": 50320,
111
+ "<|ms|>": 50282,
112
+ "<|mt|>": 50343,
113
+ "<|my|>": 50346,
114
+ "<|ne|>": 50313,
115
+ "<|nl|>": 50271,
116
+ "<|nn|>": 50342,
117
+ "<|no|>": 50288,
118
+ "<|oc|>": 50328,
119
+ "<|pa|>": 50321,
120
+ "<|pl|>": 50269,
121
+ "<|ps|>": 50340,
122
+ "<|pt|>": 50267,
123
+ "<|ro|>": 50284,
124
+ "<|ru|>": 50263,
125
+ "<|sa|>": 50344,
126
+ "<|sd|>": 50332,
127
+ "<|si|>": 50322,
128
+ "<|sk|>": 50298,
129
+ "<|sl|>": 50305,
130
+ "<|sn|>": 50324,
131
+ "<|so|>": 50326,
132
+ "<|sq|>": 50317,
133
+ "<|sr|>": 50303,
134
+ "<|su|>": 50357,
135
+ "<|sv|>": 50273,
136
+ "<|sw|>": 50318,
137
+ "<|ta|>": 50287,
138
+ "<|te|>": 50299,
139
+ "<|tg|>": 50331,
140
+ "<|th|>": 50289,
141
+ "<|tk|>": 50341,
142
+ "<|tl|>": 50348,
143
+ "<|tr|>": 50268,
144
+ "<|tt|>": 50351,
145
+ "<|uk|>": 50280,
146
+ "<|ur|>": 50290,
147
+ "<|uz|>": 50337,
148
+ "<|vi|>": 50278,
149
+ "<|yi|>": 50335,
150
+ "<|yo|>": 50325,
151
+ "<|zh|>": 50260
152
+ },
153
+ "language": "hungarian",
154
+ "max_initial_timestamp_index": 50,
155
+ "max_length": 448,
156
+ "no_timestamps_token_id": 50363,
157
+ "pad_token_id": 50257,
158
+ "prev_sot_token_id": 50361,
159
+ "return_timestamps": false,
160
+ "suppress_tokens": [
161
+ 1,
162
+ 2,
163
+ 7,
164
+ 8,
165
+ 9,
166
+ 10,
167
+ 14,
168
+ 25,
169
+ 26,
170
+ 27,
171
+ 28,
172
+ 29,
173
+ 31,
174
+ 58,
175
+ 59,
176
+ 60,
177
+ 61,
178
+ 62,
179
+ 63,
180
+ 90,
181
+ 91,
182
+ 92,
183
+ 93,
184
+ 359,
185
+ 503,
186
+ 522,
187
+ 542,
188
+ 873,
189
+ 893,
190
+ 902,
191
+ 918,
192
+ 922,
193
+ 931,
194
+ 1350,
195
+ 1853,
196
+ 1982,
197
+ 2460,
198
+ 2627,
199
+ 3246,
200
+ 3253,
201
+ 3268,
202
+ 3536,
203
+ 3846,
204
+ 3961,
205
+ 4183,
206
+ 4667,
207
+ 6585,
208
+ 6647,
209
+ 7273,
210
+ 9061,
211
+ 9383,
212
+ 10428,
213
+ 10929,
214
+ 11938,
215
+ 12033,
216
+ 12331,
217
+ 12562,
218
+ 13793,
219
+ 14157,
220
+ 14635,
221
+ 15265,
222
+ 15618,
223
+ 16553,
224
+ 16604,
225
+ 18362,
226
+ 18956,
227
+ 20075,
228
+ 21675,
229
+ 22520,
230
+ 26130,
231
+ 26161,
232
+ 26435,
233
+ 28279,
234
+ 29464,
235
+ 31650,
236
+ 32302,
237
+ 32470,
238
+ 36865,
239
+ 42863,
240
+ 47425,
241
+ 49870,
242
+ 50254,
243
+ 50258,
244
+ 50358,
245
+ 50359,
246
+ 50360,
247
+ 50361,
248
+ 50362
249
+ ],
250
+ "task": "transcribe",
251
+ "task_to_id": {
252
+ "transcribe": 50359,
253
+ "translate": 50358
254
+ },
255
+ "transformers_version": "4.41.0"
256
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d847ec82123981f16dd867be7f8ff935b9e5cc1b1a294f8832335821518d2daf
3
+ size 966995080
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280f040b65ce587df916d44930d5a60ee2e1c83c72ce3523afb6821d55ae23fc
3
+ size 1925064044
checkpoint-300/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-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5925766bc7c9e760433705e08c7a5ced7bc3b0bba189b1572dcf6c873712368
3
+ size 14244
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdb5054ec75b4d009648b5499a03d6d4808f041a64f97d61a0029d8af74116e
3
+ size 1064
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.3161551823972206,
3
+ "best_model_checkpoint": "./whisper-small-clean_2-400/checkpoint-300",
4
+ "epoch": 1.1425,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 0.07539740204811096,
14
+ "learning_rate": 5e-06,
15
+ "loss": 0.0016,
16
+ "step": 25
17
+ },
18
+ {
19
+ "epoch": 0.125,
20
+ "grad_norm": 1.139564037322998,
21
+ "learning_rate": 1e-05,
22
+ "loss": 0.0007,
23
+ "step": 50
24
+ },
25
+ {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 0.043032076209783554,
28
+ "learning_rate": 9.285714285714288e-06,
29
+ "loss": 0.0088,
30
+ "step": 75
31
+ },
32
+ {
33
+ "epoch": 0.25,
34
+ "grad_norm": 0.14359460771083832,
35
+ "learning_rate": 8.6e-06,
36
+ "loss": 0.0153,
37
+ "step": 100
38
+ },
39
+ {
40
+ "epoch": 0.25,
41
+ "eval_loss": 0.03707847744226456,
42
+ "eval_runtime": 636.4956,
43
+ "eval_samples_per_second": 2.713,
44
+ "eval_steps_per_second": 0.085,
45
+ "eval_wer": 5.7324840764331215,
46
+ "step": 100
47
+ },
48
+ {
49
+ "epoch": 0.3125,
50
+ "grad_norm": 0.2424408346414566,
51
+ "learning_rate": 7.885714285714286e-06,
52
+ "loss": 0.0108,
53
+ "step": 125
54
+ },
55
+ {
56
+ "epoch": 0.375,
57
+ "grad_norm": 0.038961008191108704,
58
+ "learning_rate": 7.1714285714285725e-06,
59
+ "loss": 0.0031,
60
+ "step": 150
61
+ },
62
+ {
63
+ "epoch": 0.4375,
64
+ "grad_norm": 2.9564356803894043,
65
+ "learning_rate": 6.4571428571428575e-06,
66
+ "loss": 0.0014,
67
+ "step": 175
68
+ },
69
+ {
70
+ "epoch": 0.5,
71
+ "grad_norm": Infinity,
72
+ "learning_rate": 5.771428571428572e-06,
73
+ "loss": 0.0363,
74
+ "step": 200
75
+ },
76
+ {
77
+ "epoch": 0.5,
78
+ "eval_loss": 0.04158010706305504,
79
+ "eval_runtime": 630.2516,
80
+ "eval_samples_per_second": 2.74,
81
+ "eval_steps_per_second": 0.086,
82
+ "eval_wer": 4.921829762594094,
83
+ "step": 200
84
+ },
85
+ {
86
+ "epoch": 0.5625,
87
+ "grad_norm": 3.3036911487579346,
88
+ "learning_rate": 5.114285714285715e-06,
89
+ "loss": 0.7511,
90
+ "step": 225
91
+ },
92
+ {
93
+ "epoch": 1.0175,
94
+ "grad_norm": 0.39931637048721313,
95
+ "learning_rate": 4.4e-06,
96
+ "loss": 0.1658,
97
+ "step": 250
98
+ },
99
+ {
100
+ "epoch": 1.08,
101
+ "grad_norm": 0.03213050216436386,
102
+ "learning_rate": 3.6857142857142857e-06,
103
+ "loss": 0.0005,
104
+ "step": 275
105
+ },
106
+ {
107
+ "epoch": 1.1425,
108
+ "grad_norm": 0.008164944127202034,
109
+ "learning_rate": 2.9714285714285716e-06,
110
+ "loss": 0.0008,
111
+ "step": 300
112
+ },
113
+ {
114
+ "epoch": 1.1425,
115
+ "eval_loss": 0.017297901213169098,
116
+ "eval_runtime": 634.7882,
117
+ "eval_samples_per_second": 2.721,
118
+ "eval_steps_per_second": 0.085,
119
+ "eval_wer": 2.3161551823972206,
120
+ "step": 300
121
+ }
122
+ ],
123
+ "logging_steps": 25,
124
+ "max_steps": 400,
125
+ "num_input_tokens_seen": 0,
126
+ "num_train_epochs": 9223372036854775807,
127
+ "save_steps": 100,
128
+ "stateful_callbacks": {
129
+ "TrainerControl": {
130
+ "args": {
131
+ "should_epoch_stop": false,
132
+ "should_evaluate": false,
133
+ "should_log": false,
134
+ "should_save": true,
135
+ "should_training_stop": false
136
+ },
137
+ "attributes": {}
138
+ }
139
+ },
140
+ "total_flos": 5.53910817374208e+18,
141
+ "train_batch_size": 64,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5330d1ff03d7e35061d2c5662e42e17f10af1ec1ffcba6b1f0eeab3e95da7cce
3
+ size 5240