_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: 400 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: 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: Model/runs/Mar17_07-52-06_7da6d8561539 logging_first_step: false logging_nan_inf_filter: true logging_steps: 400 logging_strategy: steps lr_scheduler_type: linear max_grad_norm: 1.0 max_steps: -1 metric_for_best_model: null model_class: wav2vec2-xls-r-300m mp_parameters: '' no_cuda: false num_train_epochs: 200 optim: adamw_hf output_dir: Model 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: false push_to_hub_model_id: null push_to_hub_organization: null push_to_hub_token: remove_unused_columns: true report_to: '[''mlflow'', ''tensorboard'']' resume_from_checkpoint: null run_name: Model save_on_each_node: false save_steps: 400 save_strategy: steps save_total_limit: 2 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: 1000 weight_decay: 0.0 xpu_backend: null