new_task.py

# TODO: Remove all TODO comments once the implementation is complete.
"""
TODO: Add the Paper Title on this line.
TODO: Add the paper's PDF URL (preferrably from arXiv) on this line.

TODO: Write a Short Description of the task.

Homepage: TODO: Add the URL to the task's Homepage here.
"""
from lm_eval.base import PromptSourceTask


# TODO: Add the BibTeX citation for the task.
_CITATION = """
"""


# TODO: Replace `NewTask` with the name of your Task.
class NewTask(PromptSourceTask):
    VERSION = 0
    # TODO: Add the `DATASET_PATH` string. This will be the name of the `Task`
    # dataset as denoted in HuggingFace `datasets`.
    DATASET_PATH = ""
    # TODO: Add the `DATASET_NAME` string. This is the name of a subset within
    # `DATASET_PATH`. If there aren't specific subsets you need, leave this as `None`.
    DATASET_NAME = None

    def has_training_docs(self):
        # TODO: Fill in the return with `True` if the Task has training data; else `False`.
        return False

    def has_validation_docs(self):
        # TODO: Fill in the return with `True` if the Task has validation data; else `False`.
        return False

    def has_test_docs(self):
        # TODO: Fill in the return with `True` if the Task has test data; else `False`.
        return False

    def stopping_criteria(self):
        # TODO: Denote the string where the generation should be split.
        # For example, for `coqa`, this is '\nQ:' and for `drop` '.'.
        # NOTE: You may delete this function if the task does not required generation.
        return None

    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`.
        """
        # TODO: Construct your language model requests with the request factory, `rf`,
        # and return them as an iterable.
        return []

    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.
        """
        # TODO: For each (sub)metric in the task evaluation, add a key-value pair
        # with the metric name as key and the corresponding metric result as value
        # for the current `doc`.
        return {}

    def aggregation(self):
        """
        :returns: {str: [metric_score] -> float}
            A dictionary where keys are the names of submetrics and values are
            functions that aggregate a list of metric scores
        """
        # TODO: For each (sub)metric in the task evaluation, add a key-value pair
        # with the metric name as key and an aggregation function as value which
        # determines how to combine results from each document in the dataset.
        # Check `lm_eval.metrics` to find built-in aggregation functions.
        return {}

    def higher_is_better(self):
        # TODO: For each (sub)metric in the task evaluation, add a key-value pair
        # with the metric name as key and a `bool` value determining whether or
        # not higher values of that metric are deemed better.
        return {}