INNER CODE UNIT · Python

preprocess_function

Guitaricet/relora · run_glue.py:447

    def preprocess_function(examples):
        # Tokenize the texts
        args = (
            (examples[sentence1_key],) if sentence2_key is None else (examples[sentence1_key], examples[sentence2_key])
        )
        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",

View source record →