{ "cli_args": { "base_model": "/tmp/skiredj.abderrahman_Bstar9train/base_model", "output_dir": "/tmp/skiredj.abderrahman_Bstar9train/out/output", "train_datasets": [ "/tmp/skiredj.abderrahman_Bstar9train/dat_0" ], "dev_dataset": "/home/skiredj.abderrahman/asr_flywheel/data/train_dev/dev", "dev_audio_col": "Audio", "dev_text_col": "Text", "dev_split": "test", "audio_col": "audio", "text_col": "text", "train_split": "train", "dataset_weights": null, "no_weighted_sampling": false, "ddp_bf16_compress": true, "init_optimizer_from": "/tmp/skiredj.abderrahman_Bstar9train/opt/optimizer_best.pt", "save_final_optimizer_to": null, "save_best_optimizer_to": "/tmp/skiredj.abderrahman_Bstar9train/out/output/optimizer_best.pt", "language": "ar", "task": "transcribe", "num_train_epochs": 3.0, "max_steps": -1, "learning_rate": 1e-05, "warmup_steps": 100, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 4, "gradient_accumulation_steps": 2, "fp16": false, "bf16": true, "gradient_checkpointing": false, "dataloader_num_workers": 8, "generation_max_length": 225, "sampling_rate": 16000, "max_audio_seconds": 30.0, "min_audio_seconds": 0.0, "long_audio_policy": "drop", "max_label_length": 448, "audio_decode_backend": "ffmpeg", "streaming": true, "save_steps": 1000, "eval_steps": 1000, "logging_steps": 50, "save_total_limit": 1, "save_only_model": true, "early_stopping_patience": 0, "early_stopping_threshold": 0.0, "preprocessing_num_workers": 4, "run_name": "experiment_1_Bstar_iter_9", "seed": 42, "metric_for_best_model": "wer", "greater_is_better": false, "report_to": "tensorboard", "resume_from_checkpoint": null, "eval_normalization": "arabic", "load_best_model_at_end": true, "map_cache_dir": "/tmp/skiredj.abderrahman_Bstar9train/tmp/map_cache", "local_work_dir": "/tmp/skiredj.abderrahman_Bstar9train/work", "model_local_dir": null, "data_local_dir": null, "output_local_dir": "/tmp/skiredj.abderrahman_Bstar9train/out", "rclone_transfers": 8, "rclone_checkers": 8, "sync_interval_seconds": 300, "keep_local_work_dir": true, "cleanup_downloads_early": true, "rclone_config": null, "prune_local_checkpoints_after_sync": true, "local_checkpoint_keep_n": 1 }, "resolved_training_args": { "output_dir": "/tmp/skiredj.abderrahman_Bstar9train/out/output", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "eval_strategy": "steps", "prediction_loss_only": false, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 4, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 2, "eval_accumulation_steps": null, "eval_delay": 0, "torch_empty_cache_steps": null, "learning_rate": 1e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 3.0, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 100, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "/tmp/skiredj.abderrahman_Bstar9train/out/output/runs/Oct20_11-40-04_gpu05", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 50, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 1000, "save_total_limit": 1, "save_safetensors": true, "save_on_each_node": false, "save_only_model": true, "restore_callback_states_from_checkpoint": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": 42, "jit_mode_eval": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": 1000, "dataloader_num_workers": 8, "dataloader_prefetch_factor": null, "past_index": -1, "run_name": "experiment_1_Bstar_iter_9", "disable_tqdm": false, "remove_unused_columns": false, "label_names": null, "load_best_model_at_end": true, "metric_for_best_model": "wer", "greater_is_better": false, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": { "min_num_params": 0, "xla": false, "xla_fsdp_v2": false, "xla_fsdp_grad_ckpt": false }, "fsdp_transformer_layer_cls_to_wrap": null, "accelerator_config": { "split_batches": false, "dispatch_batches": null, "even_batches": true, "use_seedable_sampler": true, "non_blocking": false, "gradient_accumulation_kwargs": null }, "parallelism_config": null, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": [ "tensorboard" ], "project": "huggingface", "trackio_space_id": "trackio", "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "", "hub_private_repo": null, "hub_always_push": false, "hub_revision": null, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "include_for_metrics": [], "eval_do_concat_batches": true, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "include_tokens_per_second": false, "include_num_input_tokens_seen": "no", "neftune_noise_alpha": null, "optim_target_modules": null, "batch_eval_metrics": false, "eval_on_start": false, "use_liger_kernel": false, "liger_kernel_config": null, "eval_use_gather_object": false, "average_tokens_across_devices": true, "sortish_sampler": false, "predict_with_generate": true, "generation_max_length": 225, "generation_num_beams": null, "generation_config": null } }