distillation/run_squad_w_distillation.py [459:516]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        processor = SquadV2Processor() if args.version_2_with_negative else SquadV1Processor()
        if evaluate:
            examples = processor.get_dev_examples(args.data_dir, filename=args.predict_file)
        else:
            examples = processor.get_train_examples(args.data_dir, filename=args.train_file)

        features, dataset = squad_convert_examples_to_features(
            examples=examples,
            tokenizer=tokenizer,
            max_seq_length=args.max_seq_length,
            doc_stride=args.doc_stride,
            max_query_length=args.max_query_length,
            is_training=not evaluate,
            return_dataset="pt",
            threads=args.threads,
        )

        if args.local_rank in [-1, 0]:
            logger.info("Saving features into cached file %s", cached_features_file)
            torch.save({"features": features, "dataset": dataset, "examples": examples}, cached_features_file)

    if args.local_rank == 0 and not evaluate:
        # Make sure only the first process in distributed training process the dataset, and the others will use the cache
        torch.distributed.barrier()

    if output_examples:
        return dataset, examples, features
    return dataset


def main():
    parser = argparse.ArgumentParser()

    # Required parameters
    parser.add_argument(
        "--model_type",
        default=None,
        type=str,
        required=True,
        help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()),
    )
    parser.add_argument(
        "--model_name_or_path",
        default=None,
        type=str,
        required=True,
        help="Path to pretrained model or model identifier from huggingface.co/models",
    )
    parser.add_argument(
        "--output_dir",
        default=None,
        type=str,
        required=True,
        help="The output directory where the model checkpoints and predictions will be written.",
    )

    # Distillation parameters (optional)
    parser.add_argument(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



movement-pruning/masked_run_squad.py [628:685]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            processor = SquadV2Processor() if args.version_2_with_negative else SquadV1Processor()
            if evaluate:
                examples = processor.get_dev_examples(args.data_dir, filename=args.predict_file)
            else:
                examples = processor.get_train_examples(args.data_dir, filename=args.train_file)

        features, dataset = squad_convert_examples_to_features(
            examples=examples,
            tokenizer=tokenizer,
            max_seq_length=args.max_seq_length,
            doc_stride=args.doc_stride,
            max_query_length=args.max_query_length,
            is_training=not evaluate,
            return_dataset="pt",
            threads=args.threads,
        )

        if args.local_rank in [-1, 0]:
            logger.info("Saving features into cached file %s", cached_features_file)
            torch.save({"features": features, "dataset": dataset, "examples": examples}, cached_features_file)

    if args.local_rank == 0 and not evaluate:
        # Make sure only the first process in distributed training process the dataset, and the others will use the cache
        torch.distributed.barrier()

    if output_examples:
        return dataset, examples, features
    return dataset


def main():
    parser = argparse.ArgumentParser()

    # Required parameters
    parser.add_argument(
        "--model_type",
        default=None,
        type=str,
        required=True,
        help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()),
    )
    parser.add_argument(
        "--model_name_or_path",
        default=None,
        type=str,
        required=True,
        help="Path to pretrained model or model identifier from huggingface.co/models",
    )
    parser.add_argument(
        "--output_dir",
        default=None,
        type=str,
        required=True,
        help="The output directory where the model checkpoints and predictions will be written.",
    )

    # Other parameters
    parser.add_argument(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -