Class Babi

test/general/lm_eval/tasks/babi.py:19–94

"""

class Babi(Task):
    VERSION = 0
    DATASET_PATH = "Muennighoff/babi"
    DATASET_NAME = None

    def has_training_docs(self):
        return True

    def has_validation_docs(self):
        return True

    def has_test_docs(self):
        return True

    def training_docs(self):
        if self.has_training_docs():
            return self.dataset["train"]

    def validation_docs(self):
        if self.has_validation_docs():
            return self.dataset["valid"]

    def test_docs(self):
        if self.has_test_docs():
            return self.dataset["test"]

    def doc_to_text(self, doc):
        return (
            doc['passage'] + doc['question']
        )

    def should_decontaminate(self):
        return False # TODO Necessary?

    def doc_to_decontamination_query(self, doc):
        return f"Passage: {doc['passage']}\nQuestion: {doc['question']}\nAnswer:"

    def doc_to_target(self, doc):
        return " " + doc['answer']

    def construct_requests(self, doc, ctx):
        """Uses RequestFactory to construct Requests and returns an iterable of
        Requests which will be sent to the LM.

        :param doc:
            The document as returned from training_docs, validation_docs, or test_docs.
        :param ctx: str
            The context string, generated by fewshot_context. This includes the natural
            language description, as well as the few shot examples, and the question
            part of the document for `doc`.
        """
        return rf.greedy_until(ctx, ["\n"])

    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