File size: 2,273 Bytes
73d6051
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
model: facebook/wav2vec2-xls-r-300m
trainer:
  _n_gpu: 1
  adafactor: false
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1.0e-08
  bf16: false
  bf16_full_eval: false
  dataloader_drop_last: false
  dataloader_num_workers: 0
  dataloader_pin_memory: true
  ddp_bucket_cap_mb: null
  ddp_find_unused_parameters: null
  debug: '[]'
  deepspeed: null
  disable_tqdm: false
  do_eval: true
  do_predict: false
  do_train: false
  eval_accumulation_steps: null
  eval_steps: 500
  evaluation_strategy: steps
  fp16: true
  fp16_backend: auto
  fp16_full_eval: false
  fp16_opt_level: O1
  gradient_accumulation_steps: 2
  gradient_checkpointing: true
  greater_is_better: null
  group_by_length: true
  half_precision_backend: amp
  hub_model_id: null
  hub_strategy: every_save
  hub_token: <HUB_TOKEN>
  ignore_data_skip: false
  label_names: null
  label_smoothing_factor: 0.0
  learning_rate: 0.0001
  length_column_name: length
  load_best_model_at_end: false
  local_rank: -1
  log_level: -1
  log_level_replica: -1
  log_on_each_node: true
  logging_dir: wav2vec2-large-xls-r-300m-Urdu-CV8/runs/Mar10_09-33-33_c7ab98cbc2d3
  logging_first_step: false
  logging_nan_inf_filter: true
  logging_steps: 500
  logging_strategy: steps
  lr_scheduler_type: linear
  max_grad_norm: 1.0
  max_steps: -1
  metric_for_best_model: null
  mp_parameters: ''
  no_cuda: false
  num_train_epochs: 200
  optim: adamw_hf
  output_dir: wav2vec2-large-xls-r-300m-Urdu-CV8
  overwrite_output_dir: false
  past_index: -1
  per_device_eval_batch_size: 8
  per_device_train_batch_size: 32
  per_gpu_eval_batch_size: null
  per_gpu_train_batch_size: null
  prediction_loss_only: false
  push_to_hub: true
  push_to_hub_model_id: null
  push_to_hub_organization: null
  push_to_hub_token: <PUSH_TO_HUB_TOKEN>
  remove_unused_columns: true
  report_to: '[''mlflow'', ''tensorboard'']'
  resume_from_checkpoint: null
  run_name: wav2vec2-large-xls-r-300m-Urdu-CV8
  save_on_each_node: false
  save_steps: 500
  save_strategy: steps
  save_total_limit: 1
  seed: 42
  sharded_ddp: '[]'
  skip_memory_metrics: true
  tf32: null
  tpu_metrics_debug: false
  tpu_num_cores: null
  use_legacy_prediction_loop: false
  warmup_ratio: 0.0
  warmup_steps: 10
  weight_decay: 0.0
  xpu_backend: null