scripts/train_jat.py [187:201]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    weights = [SAMPLE_WEIGHTS.get(t, 1.0) for t in train_dataset.keys()]

    train_dataset = interleave_datasets(
        list(train_dataset.values()),
        probabilities=[w / sum(weights) for w in weights],
        seed=training_args.seed,
        stopping_strategy="all_exhausted",
        n_contiguous=training_args.per_device_train_batch_size,
    )

    # Due to the train dataset's structure, where every 'n' consecutive samples share the same modalities, we can't
    # load all samples at once. Different sets of 'n' samples have different modalities. Therefore, we must load and
    # process each set of 'n' samples separately.
    if training_args.dispatch_batches is not False:
        raise ValueError("Make sure to pass `--dispatch_batches False`.")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



scripts/train_jat_tokenized.py [140:154]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    weights = [SAMPLE_WEIGHTS.get(t, 1.0) for t in train_dataset.keys()]

    train_dataset = interleave_datasets(
        list(train_dataset.values()),
        probabilities=[w / sum(weights) for w in weights],
        seed=training_args.seed,
        stopping_strategy="all_exhausted",
        n_contiguous=training_args.per_device_train_batch_size,
    )

    # Due to the train dataset's structure, where every 'n' consecutive samples share the same modalities, we can't
    # load all samples at once. Different sets of 'n' samples have different modalities. Therefore, we must load and
    # process each set of 'n' samples separately.
    if training_args.dispatch_batches is not False:
        raise ValueError("Make sure to pass `--dispatch_batches False`.")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -