AlexN commited on
Commit
fb5c97a
1 Parent(s): a989482

Training in progress, step 500

Browse files
.ipynb_checkpoints/added_tokens-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 51, "</s>": 52}
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForPreTraining"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.3,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.65,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 50,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.17.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 53,
106
+ "xvector_output_dim": 512
107
+ }
.ipynb_checkpoints/special_tokens_map-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "config": null, "tokenizer_type": "wav2vec2", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
.ipynb_checkpoints/vocab-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"&": 1, "'": 2, "a": 3, "b": 4, "c": 5, "d": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "j": 12, "k": 13, "l": 14, "m": 15, "n": 16, "o": 17, "p": 18, "q": 19, "r": 20, "s": 21, "t": 22, "u": 23, "v": 24, "w": 25, "x": 26, "y": 27, "z": 28, "«": 29, "´": 30, "»": 31, "à": 32, "á": 33, "â": 34, "ã": 35, "ç": 36, "è": 37, "é": 38, "ê": 39, "í": 40, "ñ": 41, "ó": 42, "ô": 43, "õ": 44, "ú": 45, "ü": 46, "š": 47, "ž": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 51, "</s>": 52}
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.3,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.65,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 50,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.17.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 53,
106
+ "xvector_output_dim": 512
107
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133b0025d559c0f1919002695ed5d2049799c36ae1b13b1fc29d4abeac4a2380
3
+ size 1262140977
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "config": null, "tokenizer_type": "wav2vec2", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a72b131552d7bdf4f3d9f27a7a1e0da4c0e810656b296557f72745333e7dbad
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"&": 1, "'": 2, "a": 3, "b": 4, "c": 5, "d": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "j": 12, "k": 13, "l": 14, "m": 15, "n": 16, "o": 17, "p": 18, "q": 19, "r": 20, "s": 21, "t": 22, "u": 23, "v": 24, "w": 25, "x": 26, "y": 27, "z": 28, "«": 29, "´": 30, "»": 31, "à": 32, "á": 33, "â": 34, "ã": 35, "ç": 36, "è": 37, "é": 38, "ê": 39, "í": 40, "ñ": 41, "ó": 42, "ô": 43, "õ": 44, "ú": 45, "ü": 46, "š": 47, "ž": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}
wandb/debug-internal.log ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20220201_214324-8dmqnlr2/logs/debug-internal.log
wandb/debug.log ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20220201_214324-8dmqnlr2/logs/debug.log
wandb/latest-run ADDED
@@ -0,0 +1 @@
 
 
1
+ run-20220201_214324-8dmqnlr2
wandb/run-20220201_214324-8dmqnlr2/files/conda-environment.yaml ADDED
File without changes
wandb/run-20220201_214324-8dmqnlr2/files/config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20220201_214324-8dmqnlr2/files/output.log ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+
4
+
5
+
6
+
7
+
8
+
9
+
10
+
11
+
12
+
13
+
14
+
15
+
16
+
17
+
18
+
19
+
20
+
21
+
22
+
23
+
24
+
25
+
26
+
27
+
28
+
29
+
30
+
31
+
32
+
33
+
34
+
35
+
36
+
37
+
38
+
39
+
40
+
41
+
42
+
43
+
44
+
45
+
46
+
47
+
48
+
49
+
50
+
51
+
52
+
53
+
54
+
55
+
56
+
57
+
58
+
59
+
60
+
61
+
62
+
63
+
64
+
65
+
66
+
67
+
68
+
69
+
70
+
71
+
72
+
73
+
74
+
75
+
76
+
77
+
78
+
79
+
80
+
81
+
82
+
83
+
84
+
85
+
86
+
87
+
88
+
89
+
90
+ 1%|█▌ | 99/7780 [04:08<2:17:38, 1.08s/it]
91
+
92
+
93
+
94
+
95
+
96
+
97
+
98
+
99
+
100
+
101
+
102
+
103
+
104
+
105
+
106
+
107
+
108
+
109
+
110
+
111
+
112
+
113
+
114
+
115
+
116
+
117
+
118
+
119
+
120
+
121
+
122
+
123
+
124
+
125
+
126
+
127
+
128
+
129
+
130
+
131
+
132
+
133
+
134
+
135
+
136
+
137
+
138
+
139
+
140
+
141
+
142
+
143
+
144
+
145
+
146
+
147
+
148
+
149
+
150
+
151
+
152
+
153
+
154
+
155
+
156
+
157
+
158
+
159
+
160
+
161
+
162
+
163
+
164
+
165
+
166
+
167
+
168
+
169
+
170
+
171
+
172
+
173
+
174
+
175
+
176
+
177
+
178
+
179
+ 3%|███▏ | 199/7780 [08:14<2:24:26, 1.14s/it]
180
+
181
+
182
+
183
+
184
+
185
+
186
+
187
+
188
+
189
+
190
+
191
+
192
+
193
+
194
+
195
+
196
+
197
+
198
+
199
+
200
+
201
+
202
+
203
+
204
+
205
+
206
+
207
+
208
+
209
+
210
+
211
+
212
+
213
+
214
+
215
+
216
+
217
+
218
+
219
+
220
+
221
+
222
+
223
+
224
+
225
+
226
+
227
+
228
+
229
+
230
+
231
+
232
+
233
+
234
+
235
+
236
+
237
+
238
+
239
+
240
+
241
+
242
+
243
+
244
+
245
+
246
+
247
+
248
+
249
+
250
+
251
+
252
+
253
+
254
+
255
+
256
+
257
+
258
+
259
+
260
+
261
+
262
+
263
+
264
+
265
+
266
+
267
+
268
+
269
+ 4%|████▋ | 300/7780 [12:19<2:14:04, 1.08s/it]
270
+
271
+
272
+
273
+
274
+
275
+
276
+
277
+
278
+
279
+
280
+
281
+
282
+
283
+
284
+
285
+
286
+
287
+
288
+
289
+
290
+
291
+
292
+
293
+
294
+
295
+
296
+
297
+
298
+
299
+
300
+
301
+
302
+
303
+
304
+
305
+
306
+
307
+
308
+
309
+
310
+
311
+
312
+
313
+
314
+
315
+
316
+
317
+
318
+
319
+
320
+
321
+
322
+
323
+
324
+
325
+
326
+
327
+
328
+
329
+
330
+
331
+
332
+
333
+
334
+
335
+
336
+
337
+
338
+
339
+
340
+
341
+
342
+
343
+
344
+
345
+
346
+
347
+
348
+
349
+
350
+
351
+
352
+
353
+
354
+
355
+
356
+
357
+ 5%|██████▎ | 399/7780 [16:35<7:56:31, 3.87s/it]
358
+
359
+
360
+
361
+
362
+
363
+
364
+
365
+
366
+
367
+
368
+
369
+
370
+
371
+
372
+
373
+
374
+
375
+
376
+
377
+
378
+
379
+
380
+
381
+
382
+
383
+
384
+
385
+
386
+
387
+
388
+
389
+
390
+
391
+
392
+
393
+
394
+
395
+
396
+
397
+
398
+
399
+
400
+
401
+
402
+
403
+
404
+
405
+
406
+
407
+
408
+
409
+
410
+
411
+
412
+
413
+
414
+
415
+
416
+
417
+
418
+
419
+
420
+
421
+
422
+
423
+
424
+
425
+
426
+
427
+
428
+
429
+
430
+
431
+
432
+
433
+
434
+
435
+
436
+
437
+
438
+
439
+
440
+
441
+
442
+
443
+
444
+
445
+
446
+
447
+
448
+
449
+ 6%|███████▉ | 499/7780 [20:46<7:04:20, 3.50s/it]
450
+ 6%|███████▉ | 500/7780 [20:49<7:04:04, 3.50s/it]The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
451
+ ***** Running Evaluation *****
452
+ Num examples = 4494
453
+ Batch size = 64
454
+
455
+
456
+
457
+
458
+
459
+
460
+
461
+
462
+
463
+
464
+
465
+
466
+
467
+
468
+
469
+
470
+
471
+
472
+
473
+
474
+
475
+
476
+
477
+
478
+
479
+
480
+
481
+
482
+
483
+
484
+
485
+
486
+
487
+
488
+
489
+
490
+
491
+
492
+
493
+
494
+
495
+
496
+
497
+
498
+
499
+
500
+
501
+
502
+
503
+
504
+
505
+
506
+
507
+
508
+
509
+
510
+
511
+
512
+
513
+
514
+
515
+
516
+
517
+
518
+
519
+
520
+
521
+
522
+
523
+ 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 71/71 [02:46<00:00, 1.75s/it]
524
+
525
+ Configuration saved in ./checkpoint-500/config.json
526
+ Model weights saved in ./checkpoint-500/pytorch_model.bin
527
+ Configuration saved in ./checkpoint-500/preprocessor_config.json
wandb/run-20220201_214324-8dmqnlr2/files/requirements.txt ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ aiohttp==3.8.1
2
+ aiosignal==1.2.0
3
+ analytics-python==1.4.0
4
+ anyio==3.5.0
5
+ appdirs==1.4.4
6
+ argon2-cffi-bindings==21.2.0
7
+ argon2-cffi==21.3.0
8
+ asgiref==3.5.0
9
+ asttokens==2.0.5
10
+ async-timeout==4.0.2
11
+ attrs==21.4.0
12
+ audioread==2.1.9
13
+ backcall==0.2.0
14
+ backoff==1.10.0
15
+ bcrypt==3.2.0
16
+ beautifulsoup4==4.9.3
17
+ black==21.12b0
18
+ bleach==4.1.0
19
+ brotlipy==0.7.0
20
+ certifi==2020.12.5
21
+ cffi==1.14.3
22
+ chardet==3.0.4
23
+ charset-normalizer==2.0.10
24
+ click==8.0.3
25
+ conda-build==3.21.4
26
+ conda-package-handling==1.7.2
27
+ conda==4.9.2
28
+ configparser==5.2.0
29
+ cryptography==3.2.1
30
+ cycler==0.11.0
31
+ datasets==1.18.2.dev0
32
+ debugpy==1.5.1
33
+ decorator==4.4.2
34
+ defusedxml==0.7.1
35
+ dill==0.3.4
36
+ dnspython==2.1.0
37
+ docker-pycreds==0.4.0
38
+ entrypoints==0.3
39
+ executing==0.8.2
40
+ fastapi==0.73.0
41
+ ffmpy==0.3.0
42
+ filelock==3.0.12
43
+ fonttools==4.29.0
44
+ frozenlist==1.3.0
45
+ fsspec==2022.1.0
46
+ gitdb==4.0.9
47
+ gitpython==3.1.26
48
+ glob2==0.7
49
+ gradio==2.7.5.2
50
+ h11==0.13.0
51
+ huggingface-hub==0.4.0
52
+ idna==2.10
53
+ importlib-resources==5.4.0
54
+ ipykernel==6.7.0
55
+ ipython-genutils==0.2.0
56
+ ipython==8.0.1
57
+ ipywidgets==7.6.3
58
+ jedi==0.17.0
59
+ jinja2==2.11.3
60
+ jiwer==2.3.0
61
+ joblib==1.1.0
62
+ json5==0.9.6
63
+ jsonschema==4.4.0
64
+ jupyter-client==7.1.2
65
+ jupyter-core==4.9.1
66
+ jupyterlab-pygments==0.1.2
67
+ jupyterlab-server==1.2.0
68
+ jupyterlab-widgets==1.0.2
69
+ jupyterlab==2.2.9
70
+ kiwisolver==1.3.2
71
+ libarchive-c==2.9
72
+ librosa==0.8.1
73
+ llvmlite==0.38.0
74
+ markdown2==2.4.2
75
+ markupsafe==1.1.1
76
+ matplotlib-inline==0.1.3
77
+ matplotlib==3.5.1
78
+ mistune==0.8.4
79
+ mkl-fft==1.3.0
80
+ mkl-random==1.1.1
81
+ mkl-service==2.3.0
82
+ monotonic==1.6
83
+ multidict==6.0.2
84
+ multiprocess==0.70.12.2
85
+ mypy-extensions==0.4.3
86
+ nano==0.10.0
87
+ nbclient==0.5.10
88
+ nbconvert==6.4.1
89
+ nbformat==5.1.3
90
+ nest-asyncio==1.5.4
91
+ notebook==6.4.8
92
+ numba==0.55.1
93
+ numpy==1.19.2
94
+ olefile==0.46
95
+ packaging==21.3
96
+ pandas==1.4.0
97
+ pandocfilters==1.5.0
98
+ paramiko==2.9.2
99
+ parso==0.8.1
100
+ pathspec==0.9.0
101
+ pathtools==0.1.2
102
+ pexpect==4.8.0
103
+ pickleshare==0.7.5
104
+ pillow==8.1.2
105
+ pip==21.3.1
106
+ pkginfo==1.7.0
107
+ platformdirs==2.4.1
108
+ pooch==1.6.0
109
+ prometheus-client==0.13.0
110
+ promise==2.3
111
+ prompt-toolkit==3.0.8
112
+ protobuf==3.19.4
113
+ psutil==5.8.0
114
+ ptyprocess==0.7.0
115
+ pure-eval==0.2.2
116
+ pyarrow==6.0.1
117
+ pycosat==0.6.3
118
+ pycparser==2.20
119
+ pycryptodome==3.13.0
120
+ pydantic==1.9.0
121
+ pydub==0.25.1
122
+ pygments==2.8.0
123
+ pynacl==1.5.0
124
+ pyopenssl==19.1.0
125
+ pyparsing==3.0.7
126
+ pyrsistent==0.18.1
127
+ pysocks==1.7.1
128
+ python-dateutil==2.8.2
129
+ python-etcd==0.4.5
130
+ python-levenshtein==0.12.2
131
+ python-multipart==0.0.5
132
+ pytz==2021.1
133
+ pyyaml==5.4.1
134
+ pyzmq==22.3.0
135
+ regex==2022.1.18
136
+ requests==2.24.0
137
+ resampy==0.2.2
138
+ ruamel-yaml==0.15.87
139
+ sacremoses==0.0.47
140
+ scikit-learn==1.0.2
141
+ scipy==1.7.3
142
+ send2trash==1.8.0
143
+ sentry-sdk==1.5.4
144
+ setuptools==50.3.1.post20201107
145
+ shortuuid==1.0.8
146
+ six==1.15.0
147
+ smmap==5.0.0
148
+ sniffio==1.2.0
149
+ soundfile==0.10.3.post1
150
+ soupsieve==2.2
151
+ stack-data==0.1.4
152
+ starlette==0.17.1
153
+ subprocess32==3.5.4
154
+ termcolor==1.1.0
155
+ terminado==0.13.1
156
+ testpath==0.5.0
157
+ threadpoolctl==3.0.0
158
+ tokenizers==0.11.4
159
+ tomli==1.2.3
160
+ torch==1.10.2
161
+ torchaudio==0.10.2
162
+ torchelastic==0.2.2
163
+ torchtext==0.9.1
164
+ torchvision==0.9.1
165
+ tornado==6.1
166
+ tqdm==4.62.3
167
+ traitlets==5.1.1
168
+ transformers==4.17.0.dev0
169
+ typing-extensions==4.0.1
170
+ urllib3==1.25.11
171
+ uvicorn==0.17.1
172
+ wandb==0.12.9
173
+ wcwidth==0.2.5
174
+ webencodings==0.5.1
175
+ wheel==0.35.1
176
+ widgetsnbextension==3.5.2
177
+ xxhash==2.0.2
178
+ yarl==1.7.2
179
+ yaspin==2.1.0
180
+ zipp==3.7.0
wandb/run-20220201_214324-8dmqnlr2/files/wandb-metadata.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-4.15.0-151-generic-x86_64-with-glibc2.10",
3
+ "python": "3.8.8",
4
+ "heartbeatAt": "2022-02-01T21:43:26.079203",
5
+ "startedAt": "2022-02-01T21:43:24.830312",
6
+ "docker": null,
7
+ "gpu": "Tesla V100S-PCIE-32GB",
8
+ "gpu_count": 1,
9
+ "cpu_count": 60,
10
+ "cuda": null,
11
+ "args": [
12
+ "--dataset_name=mozilla-foundation/common_voice_8_0",
13
+ "--model_name_or_path=facebook/wav2vec2-xls-r-300m",
14
+ "--dataset_config_name=pt",
15
+ "--cache_dir=../downloaded_data",
16
+ "--output_dir=./",
17
+ "--overwrite_output_dir",
18
+ "--num_train_epochs=20",
19
+ "--per_device_train_batch_size=64",
20
+ "--per_device_eval_batch_size=64",
21
+ "--gradient_accumulation_steps=1",
22
+ "--learning_rate=1e-4",
23
+ "--warmup_steps=2000",
24
+ "--length_column_name=input_length",
25
+ "--evaluation_strategy=steps",
26
+ "--text_column_name=sentence",
27
+ "--save_steps=500",
28
+ "--eval_steps=500",
29
+ "--logging_steps=100",
30
+ "--layerdrop=0.0",
31
+ "--activation_dropout=0.05",
32
+ "--save_total_limit=3",
33
+ "--freeze_feature_encoder",
34
+ "--feat_proj_dropout=0.0",
35
+ "--mask_time_prob=0.65",
36
+ "--mask_time_length=10",
37
+ "--mask_feature_prob=0.3",
38
+ "--mask_feature_length=10",
39
+ "--gradient_checkpointing",
40
+ "--report_to=wandb",
41
+ "--run_name=xls-r-300m-fr",
42
+ "--max_eval_samples=4500",
43
+ "--max_duration_in_seconds=10",
44
+ "--use_auth_token",
45
+ "--fp16",
46
+ "--group_by_length",
47
+ "--preprocessing_num_workers=64",
48
+ "--do_train",
49
+ "--do_eval",
50
+ "--load_best_model_at_end",
51
+ "--push_to_hub"
52
+ ],
53
+ "state": "running",
54
+ "program": "run_speech_recognition_ctc.py",
55
+ "codePath": "run_speech_recognition_ctc.py",
56
+ "git": {
57
+ "remote": "https://huggingface.co/AlexN/xls-r-300m-pt",
58
+ "commit": "a989482db2aaf328702b11eff59cc2151cab9001"
59
+ },
60
+ "email": "alexandrenap@hotmail.fr",
61
+ "root": "/workspace/xls-r-300m-pt",
62
+ "host": "job-1abccd0a-3293-4ffe-8274-9e8f841f653f",
63
+ "username": "ovh",
64
+ "executable": "/opt/conda/bin/python"
65
+ }
wandb/run-20220201_214324-8dmqnlr2/files/wandb-summary.json ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20220201_214324-8dmqnlr2/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20220201_214324-8dmqnlr2/logs/debug.log ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2022-02-01 21:43:24,834 INFO MainThread:16367 [wandb_setup.py:_flush():71] setting env: {}
2
+ 2022-02-01 21:43:24,834 INFO MainThread:16367 [wandb_setup.py:_flush():71] setting login settings: {}
3
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-pt/wandb/run-20220201_214324-8dmqnlr2/logs/debug.log
4
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-pt/wandb/run-20220201_214324-8dmqnlr2/logs/debug-internal.log
5
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [wandb_init.py:init():404] calling init triggers
6
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
7
+ config: {}
8
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [wandb_init.py:init():460] starting backend
9
+ 2022-02-01 21:43:24,835 INFO MainThread:16367 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
10
+ 2022-02-01 21:43:24,898 INFO MainThread:16367 [backend.py:ensure_launched():216] starting backend process...
11
+ 2022-02-01 21:43:24,959 INFO MainThread:16367 [backend.py:ensure_launched():221] started backend process with pid: 17074
12
+ 2022-02-01 21:43:24,963 INFO MainThread:16367 [wandb_init.py:init():469] backend started and connected
13
+ 2022-02-01 21:43:24,972 INFO MainThread:16367 [wandb_init.py:init():533] updated telemetry
14
+ 2022-02-01 21:43:25,120 INFO MainThread:16367 [wandb_init.py:init():563] communicating current version
15
+ 2022-02-01 21:43:25,868 INFO MainThread:16367 [wandb_init.py:init():568] got version response upgrade_message: "wandb version 0.12.10 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
16
+
17
+ 2022-02-01 21:43:25,869 INFO MainThread:16367 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
18
+ 2022-02-01 21:43:26,073 INFO MainThread:16367 [wandb_init.py:init():606] starting run threads in backend
19
+ 2022-02-01 21:43:26,673 INFO MainThread:16367 [wandb_run.py:_console_start():1810] atexit reg
20
+ 2022-02-01 21:43:26,674 INFO MainThread:16367 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
21
+ 2022-02-01 21:43:26,675 INFO MainThread:16367 [wandb_run.py:_redirect():1689] Redirecting console.
22
+ 2022-02-01 21:43:26,681 INFO MainThread:16367 [wandb_run.py:_redirect():1745] Redirects installed.
23
+ 2022-02-01 21:43:26,681 INFO MainThread:16367 [wandb_init.py:init():633] run started, returning control to user process
24
+ 2022-02-01 21:43:26,683 INFO MainThread:16367 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 50, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-xls-r-300m', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 53, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.65, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.3, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 64, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 20.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_21-41-58_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 3, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 64, 'eval_batch_size': 64}
25
+ 2022-02-01 21:43:26,687 INFO MainThread:16367 [wandb_watch.py:watch():43] Watching
wandb/run-20220201_214324-8dmqnlr2/run-8dmqnlr2.wandb ADDED
Binary file (3.46 MB). View file