INNER CODE UNIT · Python

result

Guitaricet/relora · run_glue.py:452

        result = tokenizer(*args, padding=padding, max_length=max_seq_length, truncation=True)

        # Map labels to IDs (not necessary for GLUE tasks)
        if label_to_id is not None and "label" in examples:
            result["label"] = [(label_to_id[l] if l != -1 else -1) for l in examples["label"]]
        return result

    with training_args.main_process_first(desc="dataset map pre-processing"):
        raw_datasets = raw_datasets.map(
            preprocess_function,
            batched=True,
            load_from_cache_file=not data_args.overwrite_cache,
            desc="Running tokenizer on dataset",
        )
    if training_args.do_train:
        if "train" not in raw_datasets:
            raise ValueError("--do_train requires a train dataset")
        train_dataset = raw_datasets["train"]

View source record →