def process_results()

in lm_eval/tasks/squadv2/task.py [0:0]


    def process_results(self, doc, results):
        """Take a single document and the LM results and evaluates, returning a
        dict where keys are the names of submetrics and values are the values of
        the metric for that one document

        :param doc:
            The document as returned from training_docs, validation_docs, or test_docs.
        :param results:
            The results of the requests created in construct_requests.
        """

        continuation, (logprob_unanswerable, _) = results

        no_answer_probability = exp(logprob_unanswerable)

        predictions = {
            "id": doc["id"],
            "prediction_text": continuation,
            "no_answer_probability": no_answer_probability,
        }

        references = {
            "id": doc["id"],
            "answers": doc["answers"],
        }

        return {
            "exact": (
                predictions,
                references,
            ),  # Exact match (the normalized answer exactly match the gold answer)
            "f1": (
                predictions,
                references,
            ),  # The F-score of predicted tokens versus the gold answer
            "HasAns_exact": (
                predictions,
                references,
            ),  # Exact match (the normalized answer exactly match the gold answer)
            "HasAns_f1": (
                predictions,
                references,
            ),  # The F-score of predicted tokens versus the gold answer
            "NoAns_exact": (
                predictions,
                references,
            ),  # Exact match (the normalized answer exactly match the gold answer)
            "NoAns_f1": (
                predictions,
                references,
            ),  # The F-score of predicted tokens versus the gold answer
            "best_exact": (
                predictions,
                references,
            ),  # Best exact match (with varying threshold)
            "best_f1": (predictions, references),  # Best F1 (with varying threshold)
        }