scripts/tokenize_stream.py [82:96]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    processor = AutoProcessor.from_pretrained(
        model_args.config_name if model_args.config_name else model_args.model_name_or_path,
        cache_dir=model_args.cache_dir,
        trust_remote_code=model_args.trust_remote_code,
    )

    # Set the tasks
    tasks = data_args.tasks
    for domain in ["atari", "babyai", "metaworld", "mujoco"]:
        if domain in tasks:
            tasks.remove(domain)
            tasks.extend([env_id for env_id in TASK_NAME_TO_ENV_ID.keys() if env_id.startswith(domain)])

    # Load the dataset
    dataset_dict = {}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



scripts/train_jat.py [109:125]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    processor = AutoProcessor.from_pretrained(
        model_args.config_name if model_args.config_name else model_args.model_name_or_path,
        cache_dir=model_args.cache_dir,
        trust_remote_code=model_args.trust_remote_code,
    )

    # Set the tasks
    tasks = data_args.tasks
    for domain in ["atari", "babyai", "metaworld", "mujoco"]:
        if domain in tasks:
            tasks.remove(domain)
            tasks.extend([env_id for env_id in TASK_NAME_TO_ENV_ID.keys() if env_id.startswith(domain)])

    # Load the dataset
    # Automatic cache is broken for parquet datasets
    # The following is a fix from https://github.com/huggingface/datasets/issues/3547#issuecomment-1252503988
    dataset_dict = {}
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -