File size: 28,608 Bytes
674171b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c7d9ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11a7c21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e89b390
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be05055
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a5a49f3
 
 
 
 
 
 
 
 
161be73
 
 
 
 
 
 
 
 
 
a167ba7
 
 
 
 
 
 
 
 
 
 
 
0f86b9d
 
 
 
 
 
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
12/15/2022 10:25:46 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
12/15/2022 10:25:46 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=1000,
evaluation_strategy=steps,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_max_length=225,
generation_num_beams=None,
gradient_accumulation_steps=1,
gradient_checkpointing=True,
greater_is_better=False,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-05,
length_column_name=input_length,
load_best_model_at_end=True,
local_rank=-1,
log_level=passive,
log_level_replica=passive,
log_on_each_node=True,
logging_dir=./runs/Dec15_10-25-46_129-146-123-136,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=25,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=5000,
metric_for_best_model=wer,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=./,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=32,
per_device_train_batch_size=64,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=True,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./,
save_on_each_node=False,
save_steps=1000,
save_strategy=steps,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
sortish_sampler=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=500,
weight_decay=0.0,
xpu_backend=None,
)
12/15/2022 10:25:46 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=True,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=1000,
evaluation_strategy=steps,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_max_length=225,
generation_num_beams=None,
gradient_accumulation_steps=1,
gradient_checkpointing=True,
greater_is_better=False,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-05,
length_column_name=input_length,
load_best_model_at_end=True,
local_rank=-1,
log_level=passive,
log_level_replica=passive,
log_on_each_node=True,
logging_dir=./runs/Dec15_10-25-46_129-146-123-136,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=25,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=5000,
metric_for_best_model=wer,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=./,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=32,
per_device_train_batch_size=64,
predict_with_generate=True,
prediction_loss_only=False,
push_to_hub=True,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=./,
save_on_each_node=False,
save_steps=1000,
save_strategy=steps,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
sortish_sampler=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=500,
weight_decay=0.0,
xpu_backend=None,
)
12/15/2022 10:25:47 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/common_voice_11_0.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpk7m0wk0t
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/common_voice_11_0.py in cache at /home/milan/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/5abdbe284df2909d62a839c9de9034226d2d813d25f7409b4088e82b7b16a366.7401280e97fd4bb6082c8bf5b5b90c47c5864c5dba05b2175fe0ed482e38da4d.py
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/README.md not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpndi89gdx
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/README.md in cache at /home/milan/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
12/15/2022 10:25:48 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/b73ba60fdf4bad8aeccea9e079a8a975a0848ca07c20abfb3101b55bed36fa78.13aef32ddbbf56a80c1e209ff39dc86e67cb27ba8666d8363e8e1a027dc02351
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/languages.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpcpyilpcc
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/languages.py in cache at /home/milan/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/44d465f76e4534ee3586b64e8d250b7ba50698d3e2cc5115b94171ad143fa776.6007f71ad33ec083cf7ce388a8da9c654779b9b1677dc3c83348ecfe8d430b8c.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/release_stats.py not found in cache or force_download set to True, downloading to /home/milan/.cache/huggingface/datasets/downloads/tmpck8q1rvs
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/resolve/main/release_stats.py in cache at /home/milan/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
12/15/2022 10:25:49 - INFO - datasets.utils.file_utils - creating metadata file for /home/milan/.cache/huggingface/datasets/downloads/42bf8b971b498e85494eaf891c3a974225ff7f47e30d70fea12a3a6e365e56d9.42cb02a0975fec649048e8496584d95e0cc43f92495c70462dfbe2affb6e2425.py
12/15/2022 10:25:49 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/15/2022 10:25:52 - INFO - datasets.info - Loading Dataset Infos from /home/milan/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f
12/15/2022 10:26:14 - WARNING - huggingface_hub.repository - /home/milan/whisper-small-cs-sk-cv11/./ is already a clone of https://huggingface.co/mikr/whisper-small-cs-sk-cv11. Make sure you pull the latest changes with `repo.git_pull()`.
{'loss': 2.6504, 'learning_rate': 4.2000000000000006e-07, 'epoch': 0.01}
{'loss': 1.9914, 'learning_rate': 9.200000000000001e-07, 'epoch': 1.0}
{'loss': 1.0697, 'learning_rate': 1.42e-06, 'epoch': 1.01}
{'loss': 0.7023, 'learning_rate': 1.9200000000000003e-06, 'epoch': 2.0}
{'loss': 0.5324, 'learning_rate': 2.42e-06, 'epoch': 2.01}
{'loss': 0.45, 'learning_rate': 2.92e-06, 'epoch': 3.0}
12/15/2022 10:50:26 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
{'loss': 0.338, 'learning_rate': 3.4200000000000007e-06, 'epoch': 3.01}
{'loss': 0.2858, 'learning_rate': 3.920000000000001e-06, 'epoch': 4.0}
{'loss': 0.2132, 'learning_rate': 4.42e-06, 'epoch': 4.01}
{'loss': 0.1557, 'learning_rate': 4.92e-06, 'epoch': 5.0}
{'loss': 0.1146, 'learning_rate': 5.420000000000001e-06, 'epoch': 5.01}
{'loss': 0.0738, 'learning_rate': 5.92e-06, 'epoch': 6.0}
{'loss': 0.0512, 'learning_rate': 6.42e-06, 'epoch': 6.01}
{'loss': 0.0324, 'learning_rate': 6.92e-06, 'epoch': 7.0}
{'loss': 0.0261, 'learning_rate': 7.420000000000001e-06, 'epoch': 7.01}
{'loss': 0.0188, 'learning_rate': 7.92e-06, 'epoch': 8.0}
{'loss': 0.0163, 'learning_rate': 8.42e-06, 'epoch': 9.0}
{'loss': 0.0139, 'learning_rate': 8.920000000000001e-06, 'epoch': 9.01}
{'loss': 0.0106, 'learning_rate': 9.42e-06, 'epoch': 10.0}
{'loss': 0.0106, 'learning_rate': 9.920000000000002e-06, 'epoch': 10.01}
{'loss': 0.0105, 'learning_rate': 9.953333333333333e-06, 'epoch': 11.0}
{'loss': 0.0101, 'learning_rate': 9.89777777777778e-06, 'epoch': 11.01}
{'loss': 0.0072, 'learning_rate': 9.842222222222223e-06, 'epoch': 12.0}
{'loss': 0.008, 'learning_rate': 9.786666666666667e-06, 'epoch': 12.01}
{'loss': 0.0057, 'learning_rate': 9.731111111111113e-06, 'epoch': 13.0}
{'loss': 0.0063, 'learning_rate': 9.675555555555555e-06, 'epoch': 13.01}
{'loss': 0.0035, 'learning_rate': 9.620000000000001e-06, 'epoch': 14.0}
{'loss': 0.0038, 'learning_rate': 9.564444444444445e-06, 'epoch': 14.01}
{'loss': 0.0054, 'learning_rate': 9.508888888888889e-06, 'epoch': 15.0}
{'loss': 0.0042, 'learning_rate': 9.453333333333335e-06, 'epoch': 15.01}
{'loss': 0.0035, 'learning_rate': 9.397777777777779e-06, 'epoch': 16.0}
{'loss': 0.0034, 'learning_rate': 9.342222222222223e-06, 'epoch': 17.0}
{'loss': 0.0032, 'learning_rate': 9.286666666666667e-06, 'epoch': 17.01}
{'loss': 0.0027, 'learning_rate': 9.231111111111111e-06, 'epoch': 18.0}
{'loss': 0.0018, 'learning_rate': 9.175555555555557e-06, 'epoch': 18.01}
{'loss': 0.0017, 'learning_rate': 9.12e-06, 'epoch': 19.0}
{'loss': 0.0022, 'learning_rate': 9.064444444444447e-06, 'epoch': 19.01}
{'loss': 0.0018, 'learning_rate': 9.008888888888889e-06, 'epoch': 20.0}
{'loss': 0.0013, 'learning_rate': 8.953333333333335e-06, 'epoch': 20.01}
{'loss': 0.001, 'learning_rate': 8.897777777777779e-06, 'epoch': 21.0}
{'eval_loss': 0.6506679058074951, 'eval_wer': 37.32746311280343, 'eval_runtime': 812.1587, 'eval_samples_per_second': 2.791, 'eval_steps_per_second': 0.087, 'epoch': 21.0}
{'loss': 0.001, 'learning_rate': 8.842222222222223e-06, 'epoch': 21.01}
{'loss': 0.0009, 'learning_rate': 8.786666666666668e-06, 'epoch': 22.0}
{'loss': 0.0008, 'learning_rate': 8.73111111111111e-06, 'epoch': 22.01}
{'loss': 0.0008, 'learning_rate': 8.675555555555556e-06, 'epoch': 23.0}
{'loss': 0.0007, 'learning_rate': 8.62e-06, 'epoch': 23.01}
{'loss': 0.0007, 'learning_rate': 8.564444444444445e-06, 'epoch': 24.0}
{'loss': 0.0006, 'learning_rate': 8.50888888888889e-06, 'epoch': 24.01}
{'loss': 0.0006, 'learning_rate': 8.453333333333334e-06, 'epoch': 25.0}
{'loss': 0.0006, 'learning_rate': 8.397777777777778e-06, 'epoch': 26.0}
{'loss': 0.0006, 'learning_rate': 8.342222222222222e-06, 'epoch': 26.01}
{'loss': 0.0006, 'learning_rate': 8.286666666666668e-06, 'epoch': 27.0}
{'loss': 0.0005, 'learning_rate': 8.231111111111112e-06, 'epoch': 27.01}
{'loss': 0.0005, 'learning_rate': 8.175555555555556e-06, 'epoch': 28.0}
{'loss': 0.0005, 'learning_rate': 8.120000000000002e-06, 'epoch': 28.01}
{'loss': 0.0005, 'learning_rate': 8.064444444444444e-06, 'epoch': 29.0}
{'loss': 0.0005, 'learning_rate': 8.00888888888889e-06, 'epoch': 29.01}
{'loss': 0.0005, 'learning_rate': 7.953333333333334e-06, 'epoch': 30.0}
{'loss': 0.0005, 'learning_rate': 7.897777777777778e-06, 'epoch': 30.01}
{'loss': 0.0004, 'learning_rate': 7.842222222222224e-06, 'epoch': 31.0}
{'loss': 0.0004, 'learning_rate': 7.786666666666666e-06, 'epoch': 31.01}
{'loss': 0.0004, 'learning_rate': 7.731111111111112e-06, 'epoch': 32.0}
{'loss': 0.0004, 'learning_rate': 7.675555555555556e-06, 'epoch': 32.01}
{'loss': 0.0004, 'learning_rate': 7.620000000000001e-06, 'epoch': 33.0}
{'loss': 0.0004, 'learning_rate': 7.564444444444446e-06, 'epoch': 34.0}
{'loss': 0.0004, 'learning_rate': 7.50888888888889e-06, 'epoch': 34.01}
{'loss': 0.0004, 'learning_rate': 7.453333333333334e-06, 'epoch': 35.0}
{'loss': 0.0004, 'learning_rate': 7.3977777777777786e-06, 'epoch': 35.01}
{'loss': 0.0004, 'learning_rate': 7.342222222222223e-06, 'epoch': 36.0}
{'loss': 0.0004, 'learning_rate': 7.2866666666666675e-06, 'epoch': 36.01}
{'loss': 0.0003, 'learning_rate': 7.231111111111112e-06, 'epoch': 37.0}
{'loss': 0.0003, 'learning_rate': 7.1755555555555556e-06, 'epoch': 37.01}
{'loss': 0.0003, 'learning_rate': 7.1200000000000004e-06, 'epoch': 38.0}
{'loss': 0.0003, 'learning_rate': 7.0644444444444445e-06, 'epoch': 38.01}
{'loss': 0.0003, 'learning_rate': 7.008888888888889e-06, 'epoch': 39.0}
{'loss': 0.0003, 'learning_rate': 6.953333333333334e-06, 'epoch': 39.01}
{'loss': 0.0003, 'learning_rate': 6.897777777777779e-06, 'epoch': 40.0}
{'loss': 0.0003, 'learning_rate': 6.842222222222222e-06, 'epoch': 40.01}
{'loss': 0.0003, 'learning_rate': 6.786666666666667e-06, 'epoch': 41.0}
{'loss': 0.0003, 'learning_rate': 6.731111111111111e-06, 'epoch': 42.0}
{'loss': 0.0003, 'learning_rate': 6.675555555555556e-06, 'epoch': 42.01}
{'eval_loss': 0.695440948009491, 'eval_wer': 36.11375535459305, 'eval_runtime': 776.4908, 'eval_samples_per_second': 2.92, 'eval_steps_per_second': 0.091, 'epoch': 42.01}
{'loss': 0.0003, 'learning_rate': 6.620000000000001e-06, 'epoch': 43.0}
{'loss': 0.0003, 'learning_rate': 6.564444444444446e-06, 'epoch': 43.01}
{'loss': 0.0003, 'learning_rate': 6.508888888888889e-06, 'epoch': 44.0}
{'loss': 0.0003, 'learning_rate': 6.453333333333334e-06, 'epoch': 44.01}
{'loss': 0.0003, 'learning_rate': 6.397777777777778e-06, 'epoch': 45.0}
{'loss': 0.0003, 'learning_rate': 6.342222222222223e-06, 'epoch': 45.01}
{'loss': 0.0003, 'learning_rate': 6.286666666666668e-06, 'epoch': 46.0}
{'loss': 0.0002, 'learning_rate': 6.231111111111111e-06, 'epoch': 46.01}
{'loss': 0.0002, 'learning_rate': 6.175555555555556e-06, 'epoch': 47.0}
{'loss': 0.0002, 'learning_rate': 6.120000000000001e-06, 'epoch': 47.01}
{'loss': 0.0002, 'learning_rate': 6.064444444444445e-06, 'epoch': 48.0}
{'loss': 0.0002, 'learning_rate': 6.00888888888889e-06, 'epoch': 48.01}
{'loss': 0.0002, 'learning_rate': 5.9533333333333345e-06, 'epoch': 49.0}
{'loss': 0.0002, 'learning_rate': 5.897777777777778e-06, 'epoch': 49.01}
{'loss': 0.0002, 'learning_rate': 5.8422222222222226e-06, 'epoch': 50.01}
{'loss': 0.0002, 'learning_rate': 5.7866666666666674e-06, 'epoch': 51.0}
{'loss': 0.0002, 'learning_rate': 5.7311111111111115e-06, 'epoch': 51.01}
{'loss': 0.0002, 'learning_rate': 5.675555555555556e-06, 'epoch': 52.0}
{'loss': 0.0002, 'learning_rate': 5.620000000000001e-06, 'epoch': 52.01}
{'loss': 0.0002, 'learning_rate': 5.5644444444444444e-06, 'epoch': 53.0}
{'loss': 0.0002, 'learning_rate': 5.508888888888889e-06, 'epoch': 53.01}
{'loss': 0.0002, 'learning_rate': 5.453333333333334e-06, 'epoch': 54.0}
{'loss': 0.0002, 'learning_rate': 5.397777777777778e-06, 'epoch': 54.01}
{'loss': 0.0002, 'learning_rate': 5.342222222222223e-06, 'epoch': 55.0}
{'loss': 0.0002, 'learning_rate': 5.286666666666666e-06, 'epoch': 55.01}
{'loss': 0.0002, 'learning_rate': 5.231111111111111e-06, 'epoch': 56.0}
{'loss': 0.0002, 'learning_rate': 5.175555555555556e-06, 'epoch': 56.01}
{'loss': 0.0002, 'learning_rate': 5.12e-06, 'epoch': 57.0}
{'loss': 0.0002, 'learning_rate': 5.064444444444445e-06, 'epoch': 57.01}
{'loss': 0.0002, 'learning_rate': 5.00888888888889e-06, 'epoch': 58.0}
{'loss': 0.0002, 'learning_rate': 4.953333333333334e-06, 'epoch': 59.0}
{'loss': 0.0002, 'learning_rate': 4.897777777777778e-06, 'epoch': 59.01}
{'loss': 0.0002, 'learning_rate': 4.842222222222223e-06, 'epoch': 60.0}
{'loss': 0.0002, 'learning_rate': 4.786666666666667e-06, 'epoch': 60.01}
{'loss': 0.0002, 'learning_rate': 4.731111111111112e-06, 'epoch': 61.0}
{'loss': 0.0002, 'learning_rate': 4.675555555555556e-06, 'epoch': 61.01}
{'loss': 0.0002, 'learning_rate': 4.620000000000001e-06, 'epoch': 62.0}
{'loss': 0.0002, 'learning_rate': 4.564444444444445e-06, 'epoch': 62.01}
{'loss': 0.0002, 'learning_rate': 4.50888888888889e-06, 'epoch': 63.0}
{'loss': 0.0002, 'learning_rate': 4.453333333333334e-06, 'epoch': 63.01}
12/15/2022 18:02:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
12/15/2022 18:02:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [2/20]
12/15/2022 18:02:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [3/20]
12/15/2022 18:02:53 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [4/20]
12/15/2022 18:03:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [5/20]
12/15/2022 18:03:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [6/20]
12/15/2022 18:03:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [7/20]
12/15/2022 18:03:53 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [8/20]
12/15/2022 18:04:08 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [9/20]
12/15/2022 18:04:23 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [10/20]
12/15/2022 18:04:38 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [11/20]
12/15/2022 18:04:43 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [12/20]
{'eval_loss': 0.7222780585289001, 'eval_wer': 35.43550690147549, 'eval_runtime': 913.8875, 'eval_samples_per_second': 2.481, 'eval_steps_per_second': 0.078, 'epoch': 63.01}
{'loss': 0.0002, 'learning_rate': 4.397777777777778e-06, 'epoch': 64.0}
{'loss': 0.0002, 'learning_rate': 4.3422222222222225e-06, 'epoch': 64.01}
{'loss': 0.0002, 'learning_rate': 4.2866666666666666e-06, 'epoch': 65.0}
{'loss': 0.0002, 'learning_rate': 4.2311111111111114e-06, 'epoch': 65.01}
{'loss': 0.0002, 'learning_rate': 4.175555555555556e-06, 'epoch': 66.0}
{'loss': 0.0002, 'learning_rate': 4.12e-06, 'epoch': 67.0}
{'loss': 0.0002, 'learning_rate': 4.064444444444444e-06, 'epoch': 67.01}
{'loss': 0.0001, 'learning_rate': 4.008888888888889e-06, 'epoch': 68.0}
{'loss': 0.0001, 'learning_rate': 3.953333333333333e-06, 'epoch': 68.01}
{'loss': 0.0001, 'learning_rate': 3.897777777777778e-06, 'epoch': 69.0}
{'loss': 0.0001, 'learning_rate': 3.842222222222223e-06, 'epoch': 69.01}
{'loss': 0.0001, 'learning_rate': 3.7866666666666667e-06, 'epoch': 70.0}
{'loss': 0.0001, 'learning_rate': 3.7311111111111116e-06, 'epoch': 70.01}
{'loss': 0.0001, 'learning_rate': 3.675555555555556e-06, 'epoch': 71.0}
{'loss': 0.0001, 'learning_rate': 3.62e-06, 'epoch': 71.01}
{'loss': 0.0001, 'learning_rate': 3.564444444444445e-06, 'epoch': 72.0}
{'loss': 0.0001, 'learning_rate': 3.508888888888889e-06, 'epoch': 72.01}
{'loss': 0.0001, 'learning_rate': 3.4533333333333334e-06, 'epoch': 73.0}
{'loss': 0.0001, 'learning_rate': 3.3977777777777783e-06, 'epoch': 73.01}
{'loss': 0.0001, 'learning_rate': 3.3422222222222224e-06, 'epoch': 74.0}
{'loss': 0.0001, 'learning_rate': 3.286666666666667e-06, 'epoch': 74.01}
{'loss': 0.0001, 'learning_rate': 3.2311111111111117e-06, 'epoch': 75.0}
{'loss': 0.0001, 'learning_rate': 3.1755555555555557e-06, 'epoch': 76.0}
{'loss': 0.0001, 'learning_rate': 3.12e-06, 'epoch': 76.01}
{'loss': 0.0001, 'learning_rate': 3.064444444444445e-06, 'epoch': 77.0}
{'loss': 0.0001, 'learning_rate': 3.008888888888889e-06, 'epoch': 77.01}
{'loss': 0.0001, 'learning_rate': 2.9533333333333336e-06, 'epoch': 78.0}
{'loss': 0.0001, 'learning_rate': 2.8977777777777785e-06, 'epoch': 78.01}
{'loss': 0.0001, 'learning_rate': 2.8422222222222225e-06, 'epoch': 79.0}
{'loss': 0.0001, 'learning_rate': 2.786666666666667e-06, 'epoch': 79.01}
{'loss': 0.0001, 'learning_rate': 2.7311111111111114e-06, 'epoch': 80.0}
{'loss': 0.0001, 'learning_rate': 2.675555555555556e-06, 'epoch': 80.01}
{'loss': 0.0001, 'learning_rate': 2.6200000000000003e-06, 'epoch': 81.0}
{'loss': 0.0001, 'learning_rate': 2.5644444444444444e-06, 'epoch': 81.01}
{'loss': 0.0001, 'learning_rate': 2.5088888888888892e-06, 'epoch': 82.0}
{'loss': 0.0001, 'learning_rate': 2.4533333333333333e-06, 'epoch': 82.01}
{'loss': 0.0001, 'learning_rate': 2.397777777777778e-06, 'epoch': 83.0}
{'loss': 0.0001, 'learning_rate': 2.342222222222222e-06, 'epoch': 84.0}
{'loss': 0.0001, 'learning_rate': 2.2866666666666667e-06, 'epoch': 84.01}
{'loss': 0.0001, 'learning_rate': 2.2311111111111115e-06, 'epoch': 85.0}
{'eval_loss': 0.7388416528701782, 'eval_wer': 35.59019514516897, 'eval_runtime': 749.6129, 'eval_samples_per_second': 3.024, 'eval_steps_per_second': 0.095, 'epoch': 85.0}
12/15/2022 20:54:52 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
{'loss': 0.0001, 'learning_rate': 2.1755555555555556e-06, 'epoch': 85.01}
{'loss': 0.0001, 'learning_rate': 2.12e-06, 'epoch': 86.0}
{'loss': 0.0001, 'learning_rate': 2.064444444444445e-06, 'epoch': 86.01}
{'loss': 0.0001, 'learning_rate': 2.008888888888889e-06, 'epoch': 87.0}
{'loss': 0.0001, 'learning_rate': 1.9533333333333334e-06, 'epoch': 87.01}
{'loss': 0.0001, 'learning_rate': 1.8977777777777779e-06, 'epoch': 88.0}
{'loss': 0.0001, 'learning_rate': 1.8422222222222225e-06, 'epoch': 88.01}
{'loss': 0.0001, 'learning_rate': 1.7866666666666668e-06, 'epoch': 89.0}
{'loss': 0.0001, 'learning_rate': 1.7311111111111112e-06, 'epoch': 89.01}
{'loss': 0.0001, 'learning_rate': 1.675555555555556e-06, 'epoch': 90.0}
{'loss': 0.0001, 'learning_rate': 1.6200000000000002e-06, 'epoch': 90.01}
{'loss': 0.0001, 'learning_rate': 1.5644444444444446e-06, 'epoch': 91.0}
{'loss': 0.0001, 'learning_rate': 1.5088888888888889e-06, 'epoch': 92.0}
{'loss': 0.0001, 'learning_rate': 1.4533333333333335e-06, 'epoch': 92.01}
{'loss': 0.0001, 'learning_rate': 1.397777777777778e-06, 'epoch': 93.0}
{'loss': 0.0001, 'learning_rate': 1.3422222222222222e-06, 'epoch': 93.01}
{'loss': 0.0001, 'learning_rate': 1.286666666666667e-06, 'epoch': 94.0}
{'loss': 0.0001, 'learning_rate': 1.2311111111111112e-06, 'epoch': 94.01}
{'loss': 0.0001, 'learning_rate': 1.1755555555555556e-06, 'epoch': 95.0}
{'loss': 0.0001, 'learning_rate': 1.12e-06, 'epoch': 95.01}
{'loss': 0.0001, 'learning_rate': 1.0644444444444445e-06, 'epoch': 96.0}
{'loss': 0.0001, 'learning_rate': 1.008888888888889e-06, 'epoch': 96.01}
{'loss': 0.0001, 'learning_rate': 9.533333333333335e-07, 'epoch': 97.0}
{'loss': 0.0001, 'learning_rate': 8.977777777777778e-07, 'epoch': 97.01}
{'loss': 0.0001, 'learning_rate': 8.422222222222224e-07, 'epoch': 98.0}
{'loss': 0.0001, 'learning_rate': 7.866666666666667e-07, 'epoch': 98.01}
{'loss': 0.0001, 'learning_rate': 7.311111111111112e-07, 'epoch': 99.0}
{'loss': 0.0001, 'learning_rate': 6.755555555555555e-07, 'epoch': 99.01}
{'loss': 0.0001, 'learning_rate': 6.200000000000001e-07, 'epoch': 100.0}
{'loss': 0.0001, 'learning_rate': 5.644444444444445e-07, 'epoch': 101.0}
{'loss': 0.0001, 'learning_rate': 5.088888888888889e-07, 'epoch': 101.01}
{'loss': 0.0001, 'learning_rate': 4.533333333333334e-07, 'epoch': 102.0}
{'loss': 0.0001, 'learning_rate': 3.9777777777777783e-07, 'epoch': 102.01}
{'loss': 0.0001, 'learning_rate': 3.422222222222223e-07, 'epoch': 103.0}
{'loss': 0.0001, 'learning_rate': 2.866666666666667e-07, 'epoch': 103.01}
{'loss': 0.0001, 'learning_rate': 2.3111111111111112e-07, 'epoch': 104.0}
{'loss': 0.0001, 'learning_rate': 1.7555555555555558e-07, 'epoch': 104.01}
{'loss': 0.0001, 'learning_rate': 1.2000000000000002e-07, 'epoch': 105.0}
{'loss': 0.0001, 'learning_rate': 6.444444444444445e-08, 'epoch': 105.01}
{'loss': 0.0001, 'learning_rate': 8.88888888888889e-09, 'epoch': 106.0}
{'eval_loss': 0.7465493083000183, 'eval_wer': 35.673488814850074, 'eval_runtime': 752.5079, 'eval_samples_per_second': 3.013, 'eval_steps_per_second': 0.094, 'epoch': 106.0}
{'train_runtime': 47208.0079, 'train_samples_per_second': 6.779, 'train_steps_per_second': 0.106, 'train_loss': 0.04440673050563782, 'epoch': 106.0}
12/15/2022 23:33:40 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
12/15/2022 23:33:40 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
12/15/2022 23:33:47 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
remote: LFS file scan complete.        
To https://huggingface.co/mikr/whisper-small-cs-sk-cv11
   e89b390..c511215  main -> main

12/15/2022 23:33:59 - WARNING - huggingface_hub.repository - To https://huggingface.co/mikr/whisper-small-cs-sk-cv11
   c511215..a5a49f3  main -> main

***** train metrics *****
  epoch                    =       106.0
  train_loss               =      0.0444
  train_runtime            = 13:06:48.00
  train_samples_per_second =       6.779
  train_steps_per_second   =       0.106
12/15/2022 23:34:02 - INFO - __main__ - *** Evaluate ***
***** eval metrics *****
  epoch                   =      106.0
  eval_loss               =     0.7223
  eval_runtime            = 0:12:11.82
  eval_samples_per_second =      3.098
  eval_steps_per_second   =      0.097
  eval_wer                =    35.4355
12/15/2022 23:46:31 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
remote: LFS file scan complete.        
To https://huggingface.co/mikr/whisper-small-cs-sk-cv11
   a5a49f3..161be73  main -> main

12/15/2022 23:46:44 - WARNING - huggingface_hub.repository - To https://huggingface.co/mikr/whisper-small-cs-sk-cv11
   161be73..a167ba7  main -> main

12/15/2022 23:46:47 - ERROR - huggingface_hub.repository - The push command with PID 1983109 failed.
12/15/2022 23:46:47 - ERROR - huggingface_hub.repository - fatal: unable to access 'https://huggingface.co/mikr/whisper-small-cs-sk-cv11/': The requested URL returned error: 504