{ "mon": { "dataset_path": "A-POR-LOS-8000/data/baby_cry_detection", "output_dir": "A-POR-LOS-8000/distilhubert-finetuned-cry-detector", "training_args": { "num_train_epochs": 10, "learning_rate": 0.00003, "warmup_ratio": 0.001, "output_dir": "A-POR-LOS-8000/distilhubert-finetuned-cry-detector", "eval_strategy": "epoch", "save_strategy": "epoch", "lr_scheduler_type": "cosine", "auto_find_batch_size": true, "per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "load_best_model_at_end": true, "greater_is_better": true, "metric_for_best_model": "accuracy", "optim": "adamw_torch", "hub_strategy": "checkpoint", "report_to": "tensorboard", "full_determinism": true, "seed": 123, "data_seed":123 } }, "class": { "dataset_path": "A-POR-LOS-8000/data/mixed_data", "output_dir": "A-POR-LOS-8000/distilhubert-finetuned-mixed-data", "training_args": { "num_train_epochs": 15, "learning_rate": 0.0003, "warmup_ratio": 0.4, "output_dir": "A-POR-LOS-8000/distilhubert-finetuned-mixed-data", "eval_strategy": "epoch", "save_strategy": "epoch", "lr_scheduler_type": "cosine", "auto_find_batch_size": true, "per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "load_best_model_at_end": true, "greater_is_better": true, "optim": "adamw_torch", "hub_strategy": "checkpoint", "report_to": "tensorboard", "full_determinism": true, "seed": 123, "data_seed":123 } } }