Function train

lumina_train.py:64–913

(args)

def train(args):
    args_util.verify_training_args(args)
    accelerator_setup.prepare_dataset_args(args, True)
    # sdxl_train_util.verify_sdxl_training_args(args)
    deepspeed_utils.prepare_deepspeed_args(args)
    setup_logging(args, reset=True)

    # temporary: backward compatibility for deprecated options. remove in the future
    if not args.skip_cache_check:
        args.skip_cache_check = args.skip_latents_validity_check

    # assert (
    #     not args.weighted_captions
    # ), "weighted_captions is not supported currently / weighted_captionsは現在サポートされていません"
    if args.cache_text_encoder_outputs_to_disk and not args.cache_text_encoder_outputs:
        logger.warning(
            "cache_text_encoder_outputs_to_disk is enabled, so cache_text_encoder_outputs is also enabled / cache_text_encoder_outputs_to_diskが有効になっているため、cache_text_encoder_outputsも有効になります"
        )
        args.cache_text_encoder_outputs = True

    if args.cpu_offload_checkpointing and not args.gradient_checkpointing:
        logger.warning(
            "cpu_offload_checkpointing is enabled, so gradient_checkpointing is also enabled / cpu_offload_checkpointingが有効になっているため、gradient_checkpointingも有効になります"
        )
        args.gradient_checkpointing = True

    # assert (
    #     args.blocks_to_swap is None or args.blocks_to_swap == 0
    # ) or not args.cpu_offload_checkpointing, "blocks_to_swap is not supported with cpu_offload_checkpointing / blocks_to_swapはcpu_offload_checkpointingと併用できません"

    cache_latents = args.cache_latents
    use_dreambooth_method = args.in_json is None

    if args.seed is not None:
        set_seed(args.seed)  # 乱数系列を初期化する

    # prepare caching strategy: this must be set before preparing dataset. because dataset may use this strategy for initialization.
    if args.cache_latents:
        latents_caching_strategy = strategy_lumina.LuminaLatentsCachingStrategy(
            args.cache_latents_to_disk, args.vae_batch_size, args.skip_cache_check
        )
        strategy_base.LatentsCachingStrategy.set_strategy(latents_caching_strategy)

    # データセットを準備する
    if args.dataset_class is None:
        blueprint_generator = BlueprintGenerator(
            ConfigSanitizer(True, True, args.masked_loss, True)
        )
        if args.dataset_config is not None:
            logger.info(f"Load dataset config from {args.dataset_config}")
            user_config = config_util.load_user_config(args.dataset_config)
            ignored = ["train_data_dir", "in_json"]
            if any(getattr(args, attr) is not None for attr in ignored):
                logger.warning(
                    "ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
                        ", ".join(ignored)
                    )
                )