File size: 12,349 Bytes
a5afdd5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
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
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
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
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
450
451
452
453
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
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
wandb_version: 1

_n_gpu:
  desc: null
  value: 1
_name_or_path:
  desc: null
  value: ./
_wandb:
  desc: null
  value:
    cli_version: 0.12.10
    framework: huggingface
    huggingface_version: 4.17.0.dev0
    is_jupyter_run: false
    is_kaggle_kernel: false
    m:
    - 1: train/global_step
      6:
      - 3
    python_version: 3.9.5
    start_time: 1646098009
    t:
      1:
      - 1
      - 5
      - 11
      2:
      - 1
      - 5
      - 11
      3:
      - 1
      - 7
      - 13
      4: 3.9.5
      5: 0.12.10
      6: 4.17.0.dev0
      8:
      - 5
adafactor:
  desc: null
  value: false
adam_beta1:
  desc: null
  value: 0.9
adam_beta2:
  desc: null
  value: 0.999
adam_epsilon:
  desc: null
  value: 1.0e-08
add_cross_attention:
  desc: null
  value: false
architectures:
  desc: null
  value:
  - SpeechEncoderDecoderModel
bad_words_ids:
  desc: null
  value: null
bf16:
  desc: null
  value: false
bf16_full_eval:
  desc: null
  value: false
bos_token_id:
  desc: null
  value: null
chunk_size_feed_forward:
  desc: null
  value: 0
cross_attention_hidden_size:
  desc: null
  value: null
dataloader_drop_last:
  desc: null
  value: false
dataloader_num_workers:
  desc: null
  value: 0
dataloader_pin_memory:
  desc: null
  value: true
ddp_bucket_cap_mb:
  desc: null
  value: None
ddp_find_unused_parameters:
  desc: null
  value: None
debug:
  desc: null
  value: '[]'
decoder:
  desc: null
  value:
    _name_or_path: gpt2-medium
    activation_function: gelu_new
    add_cross_attention: true
    architectures:
    - GPT2LMHeadModel
    attn_pdrop: 0.0
    bad_words_ids: null
    bos_token_id: 50256
    chunk_size_feed_forward: 0
    cross_attention_hidden_size: null
    decoder_start_token_id: null
    diversity_penalty: 0.0
    do_sample: false
    early_stopping: false
    embd_pdrop: 0.0
    encoder_no_repeat_ngram_size: 0
    eos_token_id: 50256
    finetuning_task: null
    forced_bos_token_id: null
    forced_eos_token_id: null
    id2label:
      '0': LABEL_0
      '1': LABEL_1
    initializer_range: 0.02
    is_decoder: true
    is_encoder_decoder: false
    label2id:
      LABEL_0: 0
      LABEL_1: 1
    layer_norm_epsilon: 1.0e-05
    length_penalty: 1.0
    max_length: 20
    min_length: 0
    model_type: gpt2
    n_ctx: 1024
    n_embd: 1024
    n_head: 16
    n_inner: null
    n_layer: 24
    n_positions: 1024
    n_special: 0
    no_repeat_ngram_size: 0
    num_beam_groups: 1
    num_beams: 1
    num_return_sequences: 1
    output_attentions: false
    output_hidden_states: false
    output_scores: false
    pad_token_id: null
    predict_special_tokens: true
    prefix: null
    problem_type: null
    pruned_heads: {}
    remove_invalid_values: false
    reorder_and_upcast_attn: false
    repetition_penalty: 1.0
    resid_pdrop: 0.0
    return_dict: true
    return_dict_in_generate: false
    scale_attn_by_inverse_layer_idx: false
    scale_attn_weights: true
    sep_token_id: null
    summary_activation: null
    summary_first_dropout: 0.0
    summary_proj_to_labels: true
    summary_type: cls_index
    summary_use_proj: true
    task_specific_params:
      text-generation:
        do_sample: true
        max_length: 50
    temperature: 1.0
    tie_encoder_decoder: false
    tie_word_embeddings: true
    tokenizer_class: null
    top_k: 50
    top_p: 1.0
    torch_dtype: null
    torchscript: false
    transformers_version: 4.17.0.dev0
    use_bfloat16: false
    use_cache: false
    vocab_size: 50257
decoder_start_token_id:
  desc: null
  value: 50256
deepspeed:
  desc: null
  value: None
disable_tqdm:
  desc: null
  value: false
diversity_penalty:
  desc: null
  value: 0.0
do_eval:
  desc: null
  value: true
do_predict:
  desc: null
  value: false
do_sample:
  desc: null
  value: false
do_train:
  desc: null
  value: true
early_stopping:
  desc: null
  value: false
encoder:
  desc: null
  value:
    _name_or_path: facebook/wav2vec2-large-lv60
    activation_dropout: 0.0
    adapter_kernel_size: 3
    adapter_stride: 2
    add_adapter: true
    add_cross_attention: false
    apply_spec_augment: false
    architectures:
    - Wav2Vec2ForPreTraining
    attention_dropout: 0.0
    bad_words_ids: null
    bos_token_id: 1
    chunk_size_feed_forward: 0
    classifier_proj_size: 256
    codevector_dim: 768
    contrastive_logits_temperature: 0.1
    conv_bias: true
    conv_dim:
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    - 512
    conv_kernel:
    - 10
    - 3
    - 3
    - 3
    - 3
    - 2
    - 2
    conv_stride:
    - 5
    - 2
    - 2
    - 2
    - 2
    - 2
    - 2
    cross_attention_hidden_size: null
    ctc_loss_reduction: sum
    ctc_zero_infinity: false
    decoder_start_token_id: null
    diversity_loss_weight: 0.1
    diversity_penalty: 0.0
    do_sample: false
    do_stable_layer_norm: true
    early_stopping: false
    encoder_no_repeat_ngram_size: 0
    eos_token_id: 2
    feat_extract_activation: gelu
    feat_extract_dropout: 0.0
    feat_extract_norm: layer
    feat_proj_dropout: 0.0
    feat_quantizer_dropout: 0.0
    final_dropout: 0.0
    finetuning_task: null
    forced_bos_token_id: null
    forced_eos_token_id: null
    gradient_checkpointing: false
    hidden_act: gelu
    hidden_dropout: 0.0
    hidden_dropout_prob: 0.0
    hidden_size: 1024
    id2label:
      '0': LABEL_0
      '1': LABEL_1
    initializer_range: 0.02
    intermediate_size: 4096
    is_decoder: false
    is_encoder_decoder: false
    label2id:
      LABEL_0: 0
      LABEL_1: 1
    layer_norm_eps: 1.0e-05
    layerdrop: 0.0
    length_penalty: 1.0
    mask_feature_length: 10
    mask_feature_min_masks: 0
    mask_feature_prob: 0.0
    mask_time_length: 10
    mask_time_min_masks: 2
    mask_time_prob: 0.0
    max_length: 20
    min_length: 0
    model_type: wav2vec2
    no_repeat_ngram_size: 0
    num_adapter_layers: 3
    num_attention_heads: 16
    num_beam_groups: 1
    num_beams: 1
    num_codevector_groups: 2
    num_codevectors_per_group: 320
    num_conv_pos_embedding_groups: 16
    num_conv_pos_embeddings: 128
    num_feat_extract_layers: 7
    num_hidden_layers: 24
    num_negatives: 100
    num_return_sequences: 1
    output_attentions: false
    output_hidden_size: 1024
    output_hidden_states: false
    output_scores: false
    pad_token_id: 0
    prefix: null
    problem_type: null
    proj_codevector_dim: 768
    pruned_heads: {}
    remove_invalid_values: false
    repetition_penalty: 1.0
    return_dict: true
    return_dict_in_generate: false
    sep_token_id: null
    task_specific_params: null
    tdnn_dilation:
    - 1
    - 2
    - 3
    - 1
    - 1
    tdnn_dim:
    - 512
    - 512
    - 512
    - 512
    - 1500
    tdnn_kernel:
    - 5
    - 3
    - 3
    - 1
    - 1
    temperature: 1.0
    tie_encoder_decoder: false
    tie_word_embeddings: true
    tokenizer_class: null
    top_k: 50
    top_p: 1.0
    torch_dtype: null
    torchscript: false
    transformers_version: 4.17.0.dev0
    use_bfloat16: false
    use_weighted_layer_sum: false
    vocab_size: 32
    xvector_output_dim: 512
encoder_no_repeat_ngram_size:
  desc: null
  value: 0
eos_token_id:
  desc: null
  value: 50256
eval_accumulation_steps:
  desc: null
  value: None
eval_batch_size:
  desc: null
  value: 16
eval_steps:
  desc: null
  value: 500
evaluation_strategy:
  desc: null
  value: steps
finetuning_task:
  desc: null
  value: null
forced_bos_token_id:
  desc: null
  value: null
forced_eos_token_id:
  desc: null
  value: null
fp16:
  desc: null
  value: true
fp16_backend:
  desc: null
  value: auto
fp16_full_eval:
  desc: null
  value: false
fp16_opt_level:
  desc: null
  value: O1
generation_max_length:
  desc: null
  value: 40
generation_num_beams:
  desc: null
  value: 1
gradient_accumulation_steps:
  desc: null
  value: 2
gradient_checkpointing:
  desc: null
  value: true
greater_is_better:
  desc: null
  value: None
group_by_length:
  desc: null
  value: true
half_precision_backend:
  desc: null
  value: amp
hub_model_id:
  desc: null
  value: None
hub_strategy:
  desc: null
  value: every_save
hub_token:
  desc: null
  value: <HUB_TOKEN>
id2label:
  desc: null
  value:
    '0': LABEL_0
    '1': LABEL_1
ignore_data_skip:
  desc: null
  value: false
is_decoder:
  desc: null
  value: false
is_encoder_decoder:
  desc: null
  value: true
label2id:
  desc: null
  value:
    LABEL_0: 0
    LABEL_1: 1
label_names:
  desc: null
  value: None
label_smoothing_factor:
  desc: null
  value: 0.0
learning_rate:
  desc: null
  value: 1.0e-05
length_column_name:
  desc: null
  value: input_length
length_penalty:
  desc: null
  value: 1.0
load_best_model_at_end:
  desc: null
  value: false
local_rank:
  desc: null
  value: -1
log_level:
  desc: null
  value: -1
log_level_replica:
  desc: null
  value: -1
log_on_each_node:
  desc: null
  value: true
logging_dir:
  desc: null
  value: ./runs/Mar01_01-26-07_sanchit--v100
logging_first_step:
  desc: null
  value: false
logging_nan_inf_filter:
  desc: null
  value: true
logging_steps:
  desc: null
  value: 1
logging_strategy:
  desc: null
  value: steps
lr_scheduler_type:
  desc: null
  value: linear
max_grad_norm:
  desc: null
  value: 1.0
max_length:
  desc: null
  value: 50
max_steps:
  desc: null
  value: -1
metric_for_best_model:
  desc: null
  value: None
min_length:
  desc: null
  value: 0
model_type:
  desc: null
  value: speech-encoder-decoder
mp_parameters:
  desc: null
  value: ''
no_cuda:
  desc: null
  value: false
no_repeat_ngram_size:
  desc: null
  value: 0
num_beam_groups:
  desc: null
  value: 1
num_beams:
  desc: null
  value: 1
num_return_sequences:
  desc: null
  value: 1
num_train_epochs:
  desc: null
  value: 1.0
optim:
  desc: null
  value: adamw_hf
output_attentions:
  desc: null
  value: false
output_dir:
  desc: null
  value: ./
output_hidden_states:
  desc: null
  value: false
output_scores:
  desc: null
  value: false
overwrite_output_dir:
  desc: null
  value: true
pad_token_id:
  desc: null
  value: 50256
past_index:
  desc: null
  value: -1
per_device_eval_batch_size:
  desc: null
  value: 16
per_device_train_batch_size:
  desc: null
  value: 16
per_gpu_eval_batch_size:
  desc: null
  value: None
per_gpu_train_batch_size:
  desc: null
  value: None
predict_with_generate:
  desc: null
  value: true
prediction_loss_only:
  desc: null
  value: false
prefix:
  desc: null
  value: null
problem_type:
  desc: null
  value: null
processor_class:
  desc: null
  value: Wav2Vec2Processor
pruned_heads:
  desc: null
  value: {}
push_to_hub:
  desc: null
  value: true
push_to_hub_model_id:
  desc: null
  value: None
push_to_hub_organization:
  desc: null
  value: None
push_to_hub_token:
  desc: null
  value: <PUSH_TO_HUB_TOKEN>
remove_invalid_values:
  desc: null
  value: false
remove_unused_columns:
  desc: null
  value: true
repetition_penalty:
  desc: null
  value: 1.0
report_to:
  desc: null
  value: '[''wandb'']'
resume_from_checkpoint:
  desc: null
  value: None
return_dict:
  desc: null
  value: true
return_dict_in_generate:
  desc: null
  value: false
run_name:
  desc: null
  value: ./
save_on_each_node:
  desc: null
  value: false
save_steps:
  desc: null
  value: 500
save_strategy:
  desc: null
  value: steps
save_total_limit:
  desc: null
  value: 1
seed:
  desc: null
  value: 42
sep_token_id:
  desc: null
  value: null
sharded_ddp:
  desc: null
  value: '[]'
skip_memory_metrics:
  desc: null
  value: true
sortish_sampler:
  desc: null
  value: false
task_specific_params:
  desc: null
  value: null
temperature:
  desc: null
  value: 1.0
tf32:
  desc: null
  value: None
tie_encoder_decoder:
  desc: null
  value: false
tie_word_embeddings:
  desc: null
  value: false
tokenizer_class:
  desc: null
  value: null
top_k:
  desc: null
  value: 50
top_p:
  desc: null
  value: 1.0
torch_dtype:
  desc: null
  value: torch.float32
torchscript:
  desc: null
  value: false
tpu_metrics_debug:
  desc: null
  value: false
tpu_num_cores:
  desc: null
  value: None
train_batch_size:
  desc: null
  value: 16
transformers_version:
  desc: null
  value: null
use_bfloat16:
  desc: null
  value: false
use_cache:
  desc: null
  value: false
use_legacy_prediction_loop:
  desc: null
  value: false
warmup_ratio:
  desc: null
  value: 0.0
warmup_steps:
  desc: null
  value: 500
weight_decay:
  desc: null
  value: 0.0
xpu_backend:
  desc: null
  value: None