FunPang commited on
Commit
4d932bb
1 Parent(s): 23180ac

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-base",
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": null,
11
+ "bos_token_id": 50257,
12
+ "classifier_proj_size": 256,
13
+ "d_model": 512,
14
+ "decoder_attention_heads": 8,
15
+ "decoder_ffn_dim": 2048,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 50258,
19
+ "dropout": 0.0,
20
+ "encoder_attention_heads": 8,
21
+ "encoder_ffn_dim": 2048,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 6,
24
+ "eos_token_id": 50257,
25
+ "forced_decoder_ids": [
26
+ [
27
+ 1,
28
+ 50259
29
+ ],
30
+ [
31
+ 2,
32
+ 50359
33
+ ],
34
+ [
35
+ 3,
36
+ 50363
37
+ ]
38
+ ],
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "mask_feature_length": 10,
42
+ "mask_feature_min_masks": 0,
43
+ "mask_feature_prob": 0.0,
44
+ "mask_time_length": 10,
45
+ "mask_time_min_masks": 2,
46
+ "mask_time_prob": 0.05,
47
+ "max_length": null,
48
+ "max_source_positions": 1500,
49
+ "max_target_positions": 448,
50
+ "median_filter_width": 7,
51
+ "model_type": "whisper",
52
+ "num_hidden_layers": 6,
53
+ "num_mel_bins": 80,
54
+ "pad_token_id": 50257,
55
+ "scale_embedding": false,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.45.0.dev0",
58
+ "use_cache": true,
59
+ "use_weighted_layer_sum": false,
60
+ "vocab_size": 51865
61
+ }
generation_config.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50257
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50258,
42
+ "eos_token_id": 50257,
43
+ "is_multilingual": true,
44
+ "lang_to_id": {
45
+ "<|af|>": 50327,
46
+ "<|am|>": 50334,
47
+ "<|ar|>": 50272,
48
+ "<|as|>": 50350,
49
+ "<|az|>": 50304,
50
+ "<|ba|>": 50355,
51
+ "<|be|>": 50330,
52
+ "<|bg|>": 50292,
53
+ "<|bn|>": 50302,
54
+ "<|bo|>": 50347,
55
+ "<|br|>": 50309,
56
+ "<|bs|>": 50315,
57
+ "<|ca|>": 50270,
58
+ "<|cs|>": 50283,
59
+ "<|cy|>": 50297,
60
+ "<|da|>": 50285,
61
+ "<|de|>": 50261,
62
+ "<|el|>": 50281,
63
+ "<|en|>": 50259,
64
+ "<|es|>": 50262,
65
+ "<|et|>": 50307,
66
+ "<|eu|>": 50310,
67
+ "<|fa|>": 50300,
68
+ "<|fi|>": 50277,
69
+ "<|fo|>": 50338,
70
+ "<|fr|>": 50265,
71
+ "<|gl|>": 50319,
72
+ "<|gu|>": 50333,
73
+ "<|haw|>": 50352,
74
+ "<|ha|>": 50354,
75
+ "<|he|>": 50279,
76
+ "<|hi|>": 50276,
77
+ "<|hr|>": 50291,
78
+ "<|ht|>": 50339,
79
+ "<|hu|>": 50286,
80
+ "<|hy|>": 50312,
81
+ "<|id|>": 50275,
82
+ "<|is|>": 50311,
83
+ "<|it|>": 50274,
84
+ "<|ja|>": 50266,
85
+ "<|jw|>": 50356,
86
+ "<|ka|>": 50329,
87
+ "<|kk|>": 50316,
88
+ "<|km|>": 50323,
89
+ "<|kn|>": 50306,
90
+ "<|ko|>": 50264,
91
+ "<|la|>": 50294,
92
+ "<|lb|>": 50345,
93
+ "<|ln|>": 50353,
94
+ "<|lo|>": 50336,
95
+ "<|lt|>": 50293,
96
+ "<|lv|>": 50301,
97
+ "<|mg|>": 50349,
98
+ "<|mi|>": 50295,
99
+ "<|mk|>": 50308,
100
+ "<|ml|>": 50296,
101
+ "<|mn|>": 50314,
102
+ "<|mr|>": 50320,
103
+ "<|ms|>": 50282,
104
+ "<|mt|>": 50343,
105
+ "<|my|>": 50346,
106
+ "<|ne|>": 50313,
107
+ "<|nl|>": 50271,
108
+ "<|nn|>": 50342,
109
+ "<|no|>": 50288,
110
+ "<|oc|>": 50328,
111
+ "<|pa|>": 50321,
112
+ "<|pl|>": 50269,
113
+ "<|ps|>": 50340,
114
+ "<|pt|>": 50267,
115
+ "<|ro|>": 50284,
116
+ "<|ru|>": 50263,
117
+ "<|sa|>": 50344,
118
+ "<|sd|>": 50332,
119
+ "<|si|>": 50322,
120
+ "<|sk|>": 50298,
121
+ "<|sl|>": 50305,
122
+ "<|sn|>": 50324,
123
+ "<|so|>": 50326,
124
+ "<|sq|>": 50317,
125
+ "<|sr|>": 50303,
126
+ "<|su|>": 50357,
127
+ "<|sv|>": 50273,
128
+ "<|sw|>": 50318,
129
+ "<|ta|>": 50287,
130
+ "<|te|>": 50299,
131
+ "<|tg|>": 50331,
132
+ "<|th|>": 50289,
133
+ "<|tk|>": 50341,
134
+ "<|tl|>": 50348,
135
+ "<|tr|>": 50268,
136
+ "<|tt|>": 50351,
137
+ "<|uk|>": 50280,
138
+ "<|ur|>": 50290,
139
+ "<|uz|>": 50337,
140
+ "<|vi|>": 50278,
141
+ "<|yi|>": 50335,
142
+ "<|yo|>": 50325,
143
+ "<|zh|>": 50260
144
+ },
145
+ "max_initial_timestamp_index": 50,
146
+ "max_length": 448,
147
+ "no_timestamps_token_id": 50363,
148
+ "pad_token_id": 50257,
149
+ "prev_sot_token_id": 50361,
150
+ "return_timestamps": false,
151
+ "suppress_tokens": [
152
+ 1,
153
+ 2,
154
+ 7,
155
+ 8,
156
+ 9,
157
+ 10,
158
+ 14,
159
+ 25,
160
+ 26,
161
+ 27,
162
+ 28,
163
+ 29,
164
+ 31,
165
+ 58,
166
+ 59,
167
+ 60,
168
+ 61,
169
+ 62,
170
+ 63,
171
+ 90,
172
+ 91,
173
+ 92,
174
+ 93,
175
+ 359,
176
+ 503,
177
+ 522,
178
+ 542,
179
+ 873,
180
+ 893,
181
+ 902,
182
+ 918,
183
+ 922,
184
+ 931,
185
+ 1350,
186
+ 1853,
187
+ 1982,
188
+ 2460,
189
+ 2627,
190
+ 3246,
191
+ 3253,
192
+ 3268,
193
+ 3536,
194
+ 3846,
195
+ 3961,
196
+ 4183,
197
+ 4667,
198
+ 6585,
199
+ 6647,
200
+ 7273,
201
+ 9061,
202
+ 9383,
203
+ 10428,
204
+ 10929,
205
+ 11938,
206
+ 12033,
207
+ 12331,
208
+ 12562,
209
+ 13793,
210
+ 14157,
211
+ 14635,
212
+ 15265,
213
+ 15618,
214
+ 16553,
215
+ 16604,
216
+ 18362,
217
+ 18956,
218
+ 20075,
219
+ 21675,
220
+ 22520,
221
+ 26130,
222
+ 26161,
223
+ 26435,
224
+ 28279,
225
+ 29464,
226
+ 31650,
227
+ 32302,
228
+ 32470,
229
+ 36865,
230
+ 42863,
231
+ 47425,
232
+ 49870,
233
+ 50254,
234
+ 50258,
235
+ 50358,
236
+ 50359,
237
+ 50360,
238
+ 50361,
239
+ 50362
240
+ ],
241
+ "task": "transcribe",
242
+ "task_to_id": {
243
+ "transcribe": 50359,
244
+ "translate": 50358
245
+ },
246
+ "transformers_version": "4.45.0.dev0"
247
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4b83d5ac37450e062c5ab346ee3125ee17eab65bbfcf9420bd68a78aaa1dbb
3
+ size 290403936
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a02949c4aaaf824e45674b4cb9a687c008744296508b1efe9a133ca636bd3d
3
+ size 574811514
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb743db0916254801973d53d82c55204e8a086c4546bb0080a1ef9be2e3d50f
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191d9bf9658be16fd2b3b5cc60b13a11e875f234fb7d688dfb547d4a067434a8
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 4.021976178493541,
3
+ "best_model_checkpoint": "model_whisper_base_atco2\\checkpoint-9108",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 12.400457382202148,
14
+ "learning_rate": 1e-05,
15
+ "loss": 0.2212,
16
+ "step": 1012
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.10344767570495605,
21
+ "eval_runtime": 291.7326,
22
+ "eval_samples_per_second": 6.945,
23
+ "eval_steps_per_second": 0.871,
24
+ "eval_wer": 5.93440697869485,
25
+ "step": 1012
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 4.802471160888672,
30
+ "learning_rate": 1e-05,
31
+ "loss": 0.0619,
32
+ "step": 2024
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.09189248830080032,
37
+ "eval_runtime": 297.8017,
38
+ "eval_samples_per_second": 6.803,
39
+ "eval_steps_per_second": 0.853,
40
+ "eval_wer": 5.183694011071967,
41
+ "step": 2024
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 4.2378997802734375,
46
+ "learning_rate": 1e-05,
47
+ "loss": 0.0273,
48
+ "step": 3036
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.08819250017404556,
53
+ "eval_runtime": 287.7608,
54
+ "eval_samples_per_second": 7.041,
55
+ "eval_steps_per_second": 0.883,
56
+ "eval_wer": 4.495889951350445,
57
+ "step": 3036
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 1.339867353439331,
62
+ "learning_rate": 1e-05,
63
+ "loss": 0.0146,
64
+ "step": 4048
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_loss": 0.0916878879070282,
69
+ "eval_runtime": 284.6865,
70
+ "eval_samples_per_second": 7.117,
71
+ "eval_steps_per_second": 0.892,
72
+ "eval_wer": 4.214896829391042,
73
+ "step": 4048
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 4.930009841918945,
78
+ "learning_rate": 1e-05,
79
+ "loss": 0.0085,
80
+ "step": 5060
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_loss": 0.09865663200616837,
85
+ "eval_runtime": 286.2104,
86
+ "eval_samples_per_second": 7.079,
87
+ "eval_steps_per_second": 0.887,
88
+ "eval_wer": 4.638483475926858,
89
+ "step": 5060
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 0.15008990466594696,
94
+ "learning_rate": 1e-05,
95
+ "loss": 0.0059,
96
+ "step": 6072
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_loss": 0.09895044565200806,
101
+ "eval_runtime": 288.0034,
102
+ "eval_samples_per_second": 7.035,
103
+ "eval_steps_per_second": 0.882,
104
+ "eval_wer": 4.999161214561315,
105
+ "step": 6072
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 0.05994468554854393,
110
+ "learning_rate": 1e-05,
111
+ "loss": 0.004,
112
+ "step": 7084
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_loss": 0.10006546229124069,
117
+ "eval_runtime": 285.4295,
118
+ "eval_samples_per_second": 7.098,
119
+ "eval_steps_per_second": 0.89,
120
+ "eval_wer": 4.172957557456803,
121
+ "step": 7084
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 0.015984803438186646,
126
+ "learning_rate": 1e-05,
127
+ "loss": 0.0039,
128
+ "step": 8096
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_loss": 0.10367220640182495,
133
+ "eval_runtime": 285.9651,
134
+ "eval_samples_per_second": 7.085,
135
+ "eval_steps_per_second": 0.888,
136
+ "eval_wer": 4.663647039087401,
137
+ "step": 8096
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 0.4414064586162567,
142
+ "learning_rate": 1e-05,
143
+ "loss": 0.0045,
144
+ "step": 9108
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_loss": 0.10489141196012497,
149
+ "eval_runtime": 284.3163,
150
+ "eval_samples_per_second": 7.126,
151
+ "eval_steps_per_second": 0.893,
152
+ "eval_wer": 4.021976178493541,
153
+ "step": 9108
154
+ },
155
+ {
156
+ "epoch": 10.0,
157
+ "grad_norm": 0.01772579923272133,
158
+ "learning_rate": 1e-05,
159
+ "loss": 0.0024,
160
+ "step": 10120
161
+ },
162
+ {
163
+ "epoch": 10.0,
164
+ "eval_loss": 0.11083633452653885,
165
+ "eval_runtime": 285.82,
166
+ "eval_samples_per_second": 7.088,
167
+ "eval_steps_per_second": 0.889,
168
+ "eval_wer": 4.265223955712129,
169
+ "step": 10120
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 10120,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 10,
176
+ "save_steps": 500,
177
+ "stateful_callbacks": {
178
+ "TrainerControl": {
179
+ "args": {
180
+ "should_epoch_stop": false,
181
+ "should_evaluate": false,
182
+ "should_log": false,
183
+ "should_save": true,
184
+ "should_training_stop": true
185
+ },
186
+ "attributes": {}
187
+ }
188
+ },
189
+ "total_flos": 5.2484708892672e+18,
190
+ "train_batch_size": 8,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dede37d146aa33ec8a494f0bbf6e1483ae5883c3fe479ffd5ee2f0df94fd2654
3
+ size 5368