File size: 9,128 Bytes
dedcdce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
_name_or_path:
    value: openai/whisper-large-v3
_wandb:
    value:
        cli_version: 0.18.3
        m:
            - "1": train/global_step
              "6":
                - 3
              "7": []
            - "1": train/epoch
              "5": 1
              "6":
                - 1
                - 3
              "7": []
        python_version: 3.12.3
        t:
            "1":
                - 1
                - 5
                - 11
                - 49
                - 51
                - 53
                - 55
                - 71
                - 100
            "2":
                - 1
                - 5
                - 11
                - 49
                - 51
                - 53
                - 55
                - 71
                - 100
            "3":
                - 7
                - 13
                - 19
                - 23
                - 55
                - 62
                - 66
            "4": 3.12.3
            "5": 0.18.3
            "6": 4.46.0.dev0
            "8":
                - 5
            "9":
                "1": transformers_trainer
            "12": 0.18.3
            "13": linux-x86_64
accelerator_config:
    value:
        dispatch_batches: null
        even_batches: true
        gradient_accumulation_kwargs: null
        non_blocking: false
        split_batches: false
        use_seedable_sampler: true
activation_dropout:
    value: 0
activation_function:
    value: gelu
adafactor:
    value: false
adam_beta1:
    value: 0.9
adam_beta2:
    value: 0.999
adam_epsilon:
    value: 1e-08
add_cross_attention:
    value: false
apply_spec_augment:
    value: false
architectures:
    value:
        - WhisperForConditionalGeneration
attention_dropout:
    value: 0
auto_find_batch_size:
    value: false
bad_words_ids:
    value: null
batch_eval_metrics:
    value: false
begin_suppress_tokens:
    value:
        - 220
        - 50257
bf16:
    value: false
bf16_full_eval:
    value: false
bos_token_id:
    value: 50257
chunk_size_feed_forward:
    value: 0
classifier_proj_size:
    value: 256
cross_attention_hidden_size:
    value: null
d_model:
    value: 1280
data_seed:
    value: null
dataloader_drop_last:
    value: false
dataloader_num_workers:
    value: 0
dataloader_persistent_workers:
    value: false
dataloader_pin_memory:
    value: true
dataloader_prefetch_factor:
    value: null
ddp_backend:
    value: null
ddp_broadcast_buffers:
    value: null
ddp_bucket_cap_mb:
    value: null
ddp_find_unused_parameters:
    value: null
ddp_timeout:
    value: 1800
debug:
    value: []
decoder_attention_heads:
    value: 20
decoder_ffn_dim:
    value: 5120
decoder_layerdrop:
    value: 0
decoder_layers:
    value: 32
decoder_start_token_id:
    value: 50258
deepspeed:
    value: null
disable_tqdm:
    value: false
dispatch_batches:
    value: null
diversity_penalty:
    value: 0
do_eval:
    value: true
do_predict:
    value: false
do_sample:
    value: false
do_train:
    value: true
dropout:
    value: 0
early_stopping:
    value: false
encoder_attention_heads:
    value: 20
encoder_ffn_dim:
    value: 5120
encoder_layerdrop:
    value: 0
encoder_layers:
    value: 32
encoder_no_repeat_ngram_size:
    value: 0
eos_token_id:
    value: 50257
eval_accumulation_steps:
    value: null
eval_delay:
    value: 0
eval_do_concat_batches:
    value: true
eval_on_start:
    value: false
eval_steps:
    value: 500
eval_strategy:
    value: steps
eval_use_gather_object:
    value: false
evaluation_strategy:
    value: steps
exponential_decay_length_penalty:
    value: null
finetuning_task:
    value: null
forced_bos_token_id:
    value: null
forced_decoder_ids:
    value: null
forced_eos_token_id:
    value: null
fp16:
    value: true
fp16_backend:
    value: auto
fp16_full_eval:
    value: false
fp16_opt_level:
    value: O1
fsdp:
    value: []
fsdp_config:
    value:
        min_num_params: 0
        xla: false
        xla_fsdp_grad_ckpt: false
        xla_fsdp_v2: false
fsdp_min_num_params:
    value: 0
fsdp_transformer_layer_cls_to_wrap:
    value: null
full_determinism:
    value: false
generation_config:
    value: null
generation_max_length:
    value: 228
generation_num_beams:
    value: null
gradient_accumulation_steps:
    value: 1
gradient_checkpointing:
    value: true
gradient_checkpointing_kwargs:
    value: null
greater_is_better:
    value: false
group_by_length:
    value: false
half_precision_backend:
    value: auto
hub_always_push:
    value: false
hub_model_id:
    value: null
hub_private_repo:
    value: false
hub_strategy:
    value: every_save
hub_token:
    value: <HUB_TOKEN>
id2label:
    value:
        "0": LABEL_0
        "1": LABEL_1
ignore_data_skip:
    value: false
include_for_metrics:
    value: []
include_inputs_for_metrics:
    value: false
include_num_input_tokens_seen:
    value: false
include_tokens_per_second:
    value: false
init_std:
    value: 0.02
is_decoder:
    value: false
is_encoder_decoder:
    value: true
jit_mode_eval:
    value: false
label_names:
    value: null
label_smoothing_factor:
    value: 0
label2id:
    value:
        LABEL_0: 0
        LABEL_1: 1
learning_rate:
    value: 4.375e-06
length_column_name:
    value: input_length
length_penalty:
    value: 1
load_best_model_at_end:
    value: true
local_rank:
    value: 0
log_level:
    value: passive
log_level_replica:
    value: warning
log_on_each_node:
    value: true
logging_dir:
    value: ./runs/Oct07_10-22-04_tknika
logging_first_step:
    value: false
logging_nan_inf_filter:
    value: true
logging_steps:
    value: 25
logging_strategy:
    value: steps
lr_scheduler_type:
    value: linear
mask_feature_length:
    value: 10
mask_feature_min_masks:
    value: 0
mask_feature_prob:
    value: 0
mask_time_length:
    value: 10
mask_time_min_masks:
    value: 2
mask_time_prob:
    value: 0.05
max_grad_norm:
    value: 1
max_length:
    value: 448
max_source_positions:
    value: 1500
max_steps:
    value: 1000
max_target_positions:
    value: 448
median_filter_width:
    value: 7
metric_for_best_model:
    value: wer
min_length:
    value: 0
model/num_parameters:
    value: 1543490560
model_type:
    value: whisper
mp_parameters:
    value: ""
neftune_noise_alpha:
    value: null
no_cuda:
    value: false
no_repeat_ngram_size:
    value: 0
num_beam_groups:
    value: 1
num_beams:
    value: 1
num_hidden_layers:
    value: 32
num_mel_bins:
    value: 128
num_return_sequences:
    value: 1
num_train_epochs:
    value: 3
optim:
    value: adamw_torch
optim_args:
    value: null
optim_target_modules:
    value: null
output_attentions:
    value: false
output_dir:
    value: ./
output_hidden_states:
    value: false
output_scores:
    value: false
overwrite_output_dir:
    value: true
pad_token_id:
    value: 50256
past_index:
    value: -1
per_device_eval_batch_size:
    value: 8
per_device_train_batch_size:
    value: 16
per_gpu_eval_batch_size:
    value: null
per_gpu_train_batch_size:
    value: null
predict_with_generate:
    value: true
prediction_loss_only:
    value: false
prefix:
    value: null
problem_type:
    value: null
push_to_hub:
    value: true
push_to_hub_model_id:
    value: null
push_to_hub_organization:
    value: null
push_to_hub_token:
    value: <PUSH_TO_HUB_TOKEN>
ray_scope:
    value: last
remove_invalid_values:
    value: false
remove_unused_columns:
    value: true
repetition_penalty:
    value: 1
report_to:
    value:
        - wandb
restore_callback_states_from_checkpoint:
    value: false
resume_from_checkpoint:
    value: ./checkpoint-9000/
return_dict:
    value: true
return_dict_in_generate:
    value: false
run_name:
    value: whisper-large-eu
save_on_each_node:
    value: false
save_only_model:
    value: false
save_safetensors:
    value: true
save_steps:
    value: 1000
save_strategy:
    value: steps
save_total_limit:
    value: null
scale_embedding:
    value: false
seed:
    value: 42
sep_token_id:
    value: null
skip_memory_metrics:
    value: true
sortish_sampler:
    value: false
split_batches:
    value: null
suppress_tokens:
    value: null
task_specific_params:
    value: null
temperature:
    value: 1
tf_legacy_loss:
    value: false
tf32:
    value: null
tie_encoder_decoder:
    value: false
tie_word_embeddings:
    value: true
tokenizer_class:
    value: null
top_k:
    value: 50
top_p:
    value: 1
torch_compile:
    value: false
torch_compile_backend:
    value: null
torch_compile_mode:
    value: null
torch_dtype:
    value: float16
torch_empty_cache_steps:
    value: null
torchdynamo:
    value: null
torchscript:
    value: false
tpu_metrics_debug:
    value: false
tpu_num_cores:
    value: null
transformers_version:
    value: 4.46.0.dev0
typical_p:
    value: 1
use_bfloat16:
    value: false
use_cache:
    value: false
use_cpu:
    value: false
use_ipex:
    value: false
use_legacy_prediction_loop:
    value: false
use_liger_kernel:
    value: false
use_mps_device:
    value: false
use_weighted_layer_sum:
    value: false
vocab_size:
    value: 51866
warmup_ratio:
    value: 0
warmup_steps:
    value: 500
weight_decay:
    value: 0