Merge pull request #317 from EleutherAI/Mistobaan/add-pre-commit

Add pre-commit

lm_eval/tasks/qa4mre.py

@@ -3,9 +3,9 @@ QA4MRE 2011-2013: Overview of Question Answering for Machine Reading Evaluation
 https://www.cs.cmu.edu/~./hovy/papers/13CLEF-QA4MRE.pdf
 
 The (English only) QA4MRE challenge which was run as a Lab at CLEF 2011-2013.
-The main objective of this exercise is to develop a methodology for evaluating 
-Machine Reading systems through Question Answering and Reading Comprehension 
-Tests. Systems should be able to extract knowledge from large volumes of text 
+The main objective of this exercise is to develop a methodology for evaluating
+Machine Reading systems through Question Answering and Reading Comprehension
+Tests. Systems should be able to extract knowledge from large volumes of text
 and use this knowledge to answer questions. Four different tasks have been
 organized during these years: Main Task, Processing Modality and Negation for
 Machine Reading, Machine Reading of Biomedical Texts about Alzheimer's disease,
@@ -23,7 +23,7 @@ _CITATION = """
     booktitle={CLEF},
     year={2013}
 }
-"""
+"""  # noqa: W605
 
 
 class QA4MRE(MultipleChoiceTask):
@@ -47,7 +47,7 @@ class QA4MRE(MultipleChoiceTask):
     def _process_doc(self, doc):
         choices = doc["answer_options"]["answer_str"]
         out_doc = {
-            "source": doc["document_str"].strip().replace("\'", "'"),
+            "source": doc["document_str"].strip().replace("'", "'"),
             "query": doc["question_str"],
             "choices": choices,
             "gold": int(doc["correct_answer_id"]) - 1,

lm_eval/tasks/qasper.py

-""" 
+"""
 A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
 https://arxiv.org/abs/2105.03011
 

lm_eval/tasks/quac.py

-"""
-QuAC: Question Answering in Context
-https://arxiv.org/abs/1808.07036 
-
-Question Answering in Context (QuAC) is a dataset for modeling, understanding, and 
-participating in information seeking dialog. Data instances consist of an interactive
-dialog between two crowd workers: (1) a student who poses a sequence of freeform
-questions to learn as much as possible about a hidden Wikipedia text, and (2)
-a teacher who answers the questions by providing short excerpts (spans) from the text.
-
-Homepage: https://quac.ai/
-"""
-import inspect
-import lm_eval.datasets.quac.quac
-from lm_eval.base import Task
-
-
-_CITATION = """
-@article{choi2018quac,
-    title={Quac: Question answering in context},
-    author={Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},
-    journal={arXiv preprint arXiv:1808.07036},
-    year={2018}
-}
-"""
-
-
-class QuAC(Task):
-    VERSION = 0
-    DATASET_PATH = inspect.getfile(lm_eval.datasets.quac.quac)
-    DATASET_NAME = None
-
-    def has_training_docs(self):
-        return True
-
-    def has_validation_docs(self):
-        return True
-
-    def has_test_docs(self):
-        return False
-
-    def training_docs(self):
-        if self._training_docs is None:
-            self._training_docs = list(map(self._process_doc, self.dataset["train"]))
-        return self._training_docs
-
-    def validation_docs(self):
-        return map(self._process_doc, self.dataset["validation"])
-
-    def test_docs(self):
-        raise NotImplementedError("QuAC has no test docs.")
-
-    def _process_doc(self, doc):
-        doc["title"] = doc['title'] + ' - ' + doc['section_title']
-        return doc
-
-    def doc_to_text(self, doc):
-        return 'TITLE: ' + doc['title'] + '\n' + 'PARAGRAPH: ' + doc['paragraph'] + '\n\n' + 'Q: ' + doc['question'] + '\n\n' + 'A: '
-
-    def should_decontaminate(self):
-        return True
-
-    def doc_to_decontamination_query(self, doc):
-        return doc['paragraph']
-
-    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`.
-        """
-        # TODO: implement evaluation.
-        raise NotImplementedError('Evaluation not implemented')
-    
-    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: implement evaluation.
-        raise NotImplementedError('Evaluation not implemented')
-
-    def aggregation(self):
-        """
-        :returns: {str: [float] -> float}
-            A dictionary where keys are the names of submetrics and values are 
-            functions that aggregate a list of metrics
-        """
-        # TODO: implement evaluation.
-        raise NotImplementedError('Evaluation not implemented')
-
-    def higher_is_better(self):
-        """
-        :returns: {str: bool}
-            A dictionary where keys are the names of submetrics and values are 
-            whether a higher value of the submetric is better
-        """
-        # TODO: implement evaluation.
-        raise NotImplementedError('Evaluation not implemented')
+"""
+QuAC: Question Answering in Context
+https://arxiv.org/abs/1808.07036
+
+Question Answering in Context (QuAC) is a dataset for modeling, understanding, and
+participating in information seeking dialog. Data instances consist of an interactive
+dialog between two crowd workers: (1) a student who poses a sequence of freeform
+questions to learn as much as possible about a hidden Wikipedia text, and (2)
+a teacher who answers the questions by providing short excerpts (spans) from the text.
+
+Homepage: https://quac.ai/
+"""
+import inspect
+import lm_eval.datasets.quac.quac
+from lm_eval.base import Task
+
+
+_CITATION = """
+@article{choi2018quac,
+    title={Quac: Question answering in context},
+    author={Choi, Eunsol and He, He and Iyyer, Mohit and Yatskar, Mark and Yih, Wen-tau and Choi, Yejin and Liang, Percy and Zettlemoyer, Luke},
+    journal={arXiv preprint arXiv:1808.07036},
+    year={2018}
+}
+"""
+
+
+class QuAC(Task):
+    VERSION = 0
+    DATASET_PATH = inspect.getfile(lm_eval.datasets.quac.quac)
+    DATASET_NAME = None
+
+    def has_training_docs(self):
+        return True
+
+    def has_validation_docs(self):
+        return True
+
+    def has_test_docs(self):
+        return False
+
+    def training_docs(self):
+        if self._training_docs is None:
+            self._training_docs = list(map(self._process_doc, self.dataset["train"]))
+        return self._training_docs
+
+    def validation_docs(self):
+        return map(self._process_doc, self.dataset["validation"])
+
+    def test_docs(self):
+        raise NotImplementedError("QuAC has no test docs.")
+
+    def _process_doc(self, doc):
+        doc["title"] = doc["title"] + " - " + doc["section_title"]
+        return doc
+
+    def doc_to_text(self, doc):
+        return (
+            "TITLE: "
+            + doc["title"]
+            + "\n"
+            + "PARAGRAPH: "
+            + doc["paragraph"]
+            + "\n\n"
+            + "Q: "
+            + doc["question"]
+            + "\n\n"
+            + "A: "
+        )
+
+    def should_decontaminate(self):
+        return True
+
+    def doc_to_decontamination_query(self, doc):
+        return doc["paragraph"]
+
+    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`.
+        """
+        # TODO: implement evaluation.
+        raise NotImplementedError("Evaluation not implemented")
+
+    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: implement evaluation.
+        raise NotImplementedError("Evaluation not implemented")
+
+    def aggregation(self):
+        """
+        :returns: {str: [float] -> float}
+            A dictionary where keys are the names of submetrics and values are
+            functions that aggregate a list of metrics
+        """
+        # TODO: implement evaluation.
+        raise NotImplementedError("Evaluation not implemented")
+
+    def higher_is_better(self):
+        """
+        :returns: {str: bool}
+            A dictionary where keys are the names of submetrics and values are
+            whether a higher value of the submetric is better
+        """
+        # TODO: implement evaluation.
+        raise NotImplementedError("Evaluation not implemented")

lm_eval/tasks/race.py

@@ -20,7 +20,7 @@ _CITATION = """
 @article{lai2017large,
     title={RACE: Large-scale ReAding Comprehension Dataset From Examinations},
     author={Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard},
-    journal={arXiv preprint arXiv:1704.04683},  
+    journal={arXiv preprint arXiv:1704.04683},
     year={2017}
 }
 """
@@ -40,7 +40,7 @@ class RACE(Task):
     DATASET_NAME = "high"
 
     cache = {}
-    letter_to_num = {'A': 0, 'B': 1, 'C': 2, 'D': 3}
+    letter_to_num = {"A": 0, "B": 1, "C": 2, "D": 3}
 
     def has_training_docs(self):
         return True
@@ -59,17 +59,27 @@ class RACE(Task):
         # is shown that one document is made per passage.
 
         r = collections.defaultdict(list)
-        for item in datasets.load_dataset(path=self.DATASET_PATH, name=self.DATASET_NAME)[set]:
-            r[item['article']].append(item)
-        
-        res = list(r.values() >> each(lambda x: {
-            'article': x[0]['article'],
-            'problems': x >> each(lambda y: {
-                'question': y['question'],
-                'answer': y['answer'],
-                'options': y['options'],
-            })
-        }))
+        for item in datasets.load_dataset(
+            path=self.DATASET_PATH, name=self.DATASET_NAME
+        )[set]:
+            r[item["article"]].append(item)
+
+        res = list(
+            r.values()
+            >> each(
+                lambda x: {
+                    "article": x[0]["article"],
+                    "problems": x
+                    >> each(
+                        lambda y: {
+                            "question": y["question"],
+                            "answer": y["answer"],
+                            "options": y["options"],
+                        }
+                    ),
+                }
+            )
+        )
 
         self.cache[set] = res
         return res
@@ -85,55 +95,56 @@ class RACE(Task):
 
     @classmethod
     def get_answer_option(cls, problem):
-        answer = cls.letter_to_num[problem['answer']]
-        return problem['options'][answer]
+        answer = cls.letter_to_num[problem["answer"]]
+        return problem["options"][answer]
 
     @classmethod
     def last_problem(cls, doc):
-        return doc['problems'][-1]
+        return doc["problems"][-1]
 
     def doc_to_text(self, doc):
-        text = 'Article: ' + doc['article'] + '\n\n'
-        for problem in doc['problems'][:-1]:
-            if problem['question'][-6:] == '  _  .':
-                text += problem['question'][-5:] + self.get_answer_option(problem) + '\n'
+        text = "Article: " + doc["article"] + "\n\n"
+        for problem in doc["problems"][:-1]:
+            if problem["question"][-6:] == "  _  .":
+                text += (
+                    problem["question"][-5:] + self.get_answer_option(problem) + "\n"
+                )
             else:
-                question = 'Question: ' + problem['question'] + '\n'
-                answer = 'Answer: ' + self.get_answer_option(problem) + '\n'
+                question = "Question: " + problem["question"] + "\n"
+                answer = "Answer: " + self.get_answer_option(problem) + "\n"
                 text += question + answer
-        text += self.last_problem(doc)['question']
+        text += self.last_problem(doc)["question"]
         return text
 
     def should_decontaminate(self):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return doc['article']
+        return doc["article"]
 
     def doc_to_target(self, doc):
         return " " + self.get_answer_option(self.last_problem(doc))
 
     def construct_requests(self, doc, ctx):
-        """ Uses RequestFactory to construct Requests and returns an iterable of 
+        """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 
+            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`. 
+            part of the document for `doc`.
         """
         problem = self.last_problem(doc)
         ll_choices = [
-            rf.loglikelihood(ctx, " " + problem['options'][i])[0]
-            for i in range(4)
+            rf.loglikelihood(ctx, " " + problem["options"][i])[0] for i in range(4)
         ]
         return ll_choices
 
     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 
+        """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:
@@ -141,28 +152,22 @@ class RACE(Task):
         :param results:
             The results of the requests created in construct_requests.
         """
-        gold = self.letter_to_num[self.last_problem(doc)['answer']]
+        gold = self.letter_to_num[self.last_problem(doc)["answer"]]
         pred = np.argmax(results)
-        return {
-            "acc": int(pred == gold)
-        }
+        return {"acc": int(pred == gold)}
 
     def aggregation(self):
         """
         :returns: {str: [float] -> float}
-            A dictionary where keys are the names of submetrics and values are 
+            A dictionary where keys are the names of submetrics and values are
             functions that aggregate a list of metrics
         """
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
     def higher_is_better(self):
         """
         :returns: {str: bool}
-            A dictionary where keys are the names of submetrics and values are 
+            A dictionary where keys are the names of submetrics and values are
             whether a higher value of the submetric is better
         """
-        return {
-            "acc": True
-        }
+        return {"acc": True}

lm_eval/tasks/sat.py

@@ -59,14 +59,16 @@ class SATAnalogies(MultipleChoiceTask):
 
     def _process_doc(self, doc):
         return {
-            'source': doc['source'],
-            'query': doc['stem'].split(' ')[:2],
-            'choices': ["{} is to {}".format(*c.split(' ')[:2]) for c in doc["choices"]],
-            'gold': ['a', 'b', 'c', 'd', 'e'].index(doc['solution'].strip()),
+            "source": doc["source"],
+            "query": doc["stem"].split(" ")[:2],
+            "choices": [
+                "{} is to {}".format(*c.split(" ")[:2]) for c in doc["choices"]
+            ],
+            "gold": ["a", "b", "c", "d", "e"].index(doc["solution"].strip()),
         }
 
     def doc_to_text(self, doc):
-        return "{} is to {} as".format(*doc['query'])
+        return "{} is to {} as".format(*doc["query"])
 
     def should_decontaminate(self):
         return True

lm_eval/tasks/sciq.py

@@ -54,10 +54,10 @@ class SciQ(MultipleChoiceTask):
             doc["distractor3"],
             doc["correct_answer"],
         ]
-        src = doc['support']
+        src = doc["support"]
         out_doc = {
             "source": src,
-            "query": doc['question'],
+            "query": doc["question"],
             "choices": choices,
             "gold": 3,
         }

lm_eval/tasks/squad.py

-"""
-Know What You Don’t Know: Unanswerable Questions for SQuAD
-https://arxiv.org/pdf/1806.03822.pdf
-
-Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset,
-consisting of questions posed by crowdworkers on a set of Wikipedia articles,
-where the answer to every question is a segment of text, or span, from the
-corresponding reading passage, or the question might be unanswerable.
-SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable
-questions written adversarially by crowdworkers to look similar to answerable ones.
-To do well on SQuAD2.0, systems must not only answer questions when possible, but
-also determine when no answer is supported by the paragraph and abstain from answering.
-
-Homepage: https://rajpurkar.github.io/SQuAD-explorer/
-"""
-import datasets
-from math import exp
-from lm_eval.base import rf, Task
-from functools import partial
-from packaging import version
-
-
-_CITATION = """
-@misc{rajpurkar2018know,
-    title={Know What You Don't Know: Unanswerable Questions for SQuAD}, 
-    author={Pranav Rajpurkar and Robin Jia and Percy Liang},
-    year={2018},
-    eprint={1806.03822},
-    archivePrefix={arXiv},
-    primaryClass={cs.CL}
-}
-"""
-
-
-def _squad_metric(predictions, references):
-    squad_metric = datasets.load_metric("squad_v2")
-    return squad_metric.compute(predictions=predictions, references=references)
-
-
-def _squad_agg(key, items):
-    predictions, references = zip(*items)
-
-    return _squad_metric(predictions=predictions, references=references)[key]
-
-
-class SQuAD2(Task):
-    VERSION = 1
-    DATASET_PATH = "squad_v2"
-    DATASET_NAME = None
-
-    # HF changed squad on us so we have to make sure we aren't running the old one
-    assert version.parse(datasets.__version__) >= version.parse("1.11.0"), "datasets v1.11.0 or later required for SQuAD"
-
-    def has_training_docs(self):
-        return True
-
-    def has_validation_docs(self):
-        return True
-
-    def has_test_docs(self):
-        return False
-
-    def training_docs(self):
-        return self.dataset["train"]
-
-    def validation_docs(self):
-        return self.dataset["validation"]
-
-    def doc_to_text(self, doc):
-        return 'Title: ' + doc['title'] + '\n\n' + 'Background: ' + doc['context'] + '\n\n' + 'Question: ' + doc['question'] + '\n\n' + 'Answer:'
-
-    def should_decontaminate(self):
-        return True
-
-    def doc_to_decontamination_query(self, doc):
-        return doc['context']
-
-    def doc_to_target(self, doc):
-        answer_list = doc['answers']['text']
-        if len(answer_list) > 0:
-            answer = answer_list[0]
-        else:
-            answer = 'unanswerable'
-        return " " + 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`. 
-        """
-        continuation = rf.greedy_until(ctx, ['\n'])
-        is_unanswerable = rf.loglikelihood(ctx, " " + "unanswerable")
-        return continuation, is_unanswerable
-    
-    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)
-        }
-
-    def aggregation(self):
-        """
-        :returns: {str: [float] -> float}
-            A dictionary where keys are the names of submetrics and values are 
-            functions that aggregate a list of metrics
-        """
-        return { 
-            'exact': partial(_squad_agg, 'exact'), # Exact match (the normalized answer exactly match the gold answer)
-            'f1': partial(_squad_agg, 'f1'), #  The F-score of predicted tokens versus the gold answer
-            'HasAns_exact': partial(_squad_agg, 'HasAns_exact'), # Exact match (the normalized answer exactly match the gold answer)
-            'HasAns_f1': partial(_squad_agg, 'HasAns_f1'), # The F-score of predicted tokens versus the gold answer
-            'NoAns_exact': partial(_squad_agg, 'NoAns_exact'), # Exact match (the normalized answer exactly match the gold answer)
-            'NoAns_f1': partial(_squad_agg, 'NoAns_f1'), # The F-score of predicted tokens versus the gold answer
-            'best_exact': partial(_squad_agg, 'best_exact'), # Best exact match (with varying threshold)
-            'best_f1': partial(_squad_agg, 'best_f1'), # Best F1 (with varying threshold)
-        }
-
-    def higher_is_better(self):
-        """
-        :returns: {str: bool}
-            A dictionary where keys are the names of submetrics and values are 
-            whether a higher value of the submetric is better
-        """
-        return { 
-            'exact': True, # Exact match (the normalized answer exactly match the gold answer)
-            'f1': True, #  The F-score of predicted tokens versus the gold answer
-            'HasAns_exact': True, # Exact match (the normalized answer exactly match the gold answer)
-            'HasAns_f1': True, # The F-score of predicted tokens versus the gold answer
-            'NoAns_exact': True, # Exact match (the normalized answer exactly match the gold answer)
-            'NoAns_f1': True, # The F-score of predicted tokens versus the gold answer
-            'best_exact': True, # Best exact match (with varying threshold)
-            'best_f1': True, # Best F1 (with varying threshold)
-        }
+"""
+Know What You Don’t Know: Unanswerable Questions for SQuAD
+https://arxiv.org/pdf/1806.03822.pdf
+
+Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset,
+consisting of questions posed by crowdworkers on a set of Wikipedia articles,
+where the answer to every question is a segment of text, or span, from the
+corresponding reading passage, or the question might be unanswerable.
+SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable
+questions written adversarially by crowdworkers to look similar to answerable ones.
+To do well on SQuAD2.0, systems must not only answer questions when possible, but
+also determine when no answer is supported by the paragraph and abstain from answering.
+
+Homepage: https://rajpurkar.github.io/SQuAD-explorer/
+"""
+import datasets
+from math import exp
+from lm_eval.base import rf, Task
+from functools import partial
+from packaging import version
+
+
+_CITATION = """
+@misc{rajpurkar2018know,
+    title={Know What You Don't Know: Unanswerable Questions for SQuAD},
+    author={Pranav Rajpurkar and Robin Jia and Percy Liang},
+    year={2018},
+    eprint={1806.03822},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+"""
+
+
+def _squad_metric(predictions, references):
+    squad_metric = datasets.load_metric("squad_v2")
+    return squad_metric.compute(predictions=predictions, references=references)
+
+
+def _squad_agg(key, items):
+    predictions, references = zip(*items)
+
+    return _squad_metric(predictions=predictions, references=references)[key]
+
+
+class SQuAD2(Task):
+    VERSION = 1
+    DATASET_PATH = "squad_v2"
+    DATASET_NAME = None
+
+    # HF changed squad on us so we have to make sure we aren't running the old one
+    assert version.parse(datasets.__version__) >= version.parse(
+        "1.11.0"
+    ), "datasets v1.11.0 or later required for SQuAD"
+
+    def has_training_docs(self):
+        return True
+
+    def has_validation_docs(self):
+        return True
+
+    def has_test_docs(self):
+        return False
+
+    def training_docs(self):
+        return self.dataset["train"]
+
+    def validation_docs(self):
+        return self.dataset["validation"]
+
+    def doc_to_text(self, doc):
+        return (
+            "Title: "
+            + doc["title"]
+            + "\n\n"
+            + "Background: "
+            + doc["context"]
+            + "\n\n"
+            + "Question: "
+            + doc["question"]
+            + "\n\n"
+            + "Answer:"
+        )
+
+    def should_decontaminate(self):
+        return True
+
+    def doc_to_decontamination_query(self, doc):
+        return doc["context"]
+
+    def doc_to_target(self, doc):
+        answer_list = doc["answers"]["text"]
+        if len(answer_list) > 0:
+            answer = answer_list[0]
+        else:
+            answer = "unanswerable"
+        return " " + 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`.
+        """
+        continuation = rf.greedy_until(ctx, ["\n"])
+        is_unanswerable = rf.loglikelihood(ctx, " " + "unanswerable")
+        return continuation, is_unanswerable
+
+    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)
+        }
+
+    def aggregation(self):
+        """
+        :returns: {str: [float] -> float}
+            A dictionary where keys are the names of submetrics and values are
+            functions that aggregate a list of metrics
+        """
+        return {
+            "exact": partial(
+                _squad_agg, "exact"
+            ),  # Exact match (the normalized answer exactly match the gold answer)
+            "f1": partial(
+                _squad_agg, "f1"
+            ),  # The F-score of predicted tokens versus the gold answer
+            "HasAns_exact": partial(
+                _squad_agg, "HasAns_exact"
+            ),  # Exact match (the normalized answer exactly match the gold answer)
+            "HasAns_f1": partial(
+                _squad_agg, "HasAns_f1"
+            ),  # The F-score of predicted tokens versus the gold answer
+            "NoAns_exact": partial(
+                _squad_agg, "NoAns_exact"
+            ),  # Exact match (the normalized answer exactly match the gold answer)
+            "NoAns_f1": partial(
+                _squad_agg, "NoAns_f1"
+            ),  # The F-score of predicted tokens versus the gold answer
+            "best_exact": partial(
+                _squad_agg, "best_exact"
+            ),  # Best exact match (with varying threshold)
+            "best_f1": partial(
+                _squad_agg, "best_f1"
+            ),  # Best F1 (with varying threshold)
+        }
+
+    def higher_is_better(self):
+        """
+        :returns: {str: bool}
+            A dictionary where keys are the names of submetrics and values are
+            whether a higher value of the submetric is better
+        """
+        return {
+            "exact": True,  # Exact match (the normalized answer exactly match the gold answer)
+            "f1": True,  # The F-score of predicted tokens versus the gold answer
+            "HasAns_exact": True,  # Exact match (the normalized answer exactly match the gold answer)
+            "HasAns_f1": True,  # The F-score of predicted tokens versus the gold answer
+            "NoAns_exact": True,  # Exact match (the normalized answer exactly match the gold answer)
+            "NoAns_f1": True,  # The F-score of predicted tokens versus the gold answer
+            "best_exact": True,  # Best exact match (with varying threshold)
+            "best_f1": True,  # Best F1 (with varying threshold)
+        }

lm_eval/tasks/storycloze.py

@@ -65,23 +65,27 @@ class StoryCloze(Task):
         return self.dataset["test"]
 
     def doc_to_text(self, doc):
-        return ' '.join([
-            doc["input_sentence_1"],
-            doc["input_sentence_2"],
-            doc["input_sentence_3"],
-            doc["input_sentence_4"],
-        ])
+        return " ".join(
+            [
+                doc["input_sentence_1"],
+                doc["input_sentence_2"],
+                doc["input_sentence_3"],
+                doc["input_sentence_4"],
+            ]
+        )
 
     def should_decontaminate(self):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return ' '.join([
-            doc["input_sentence_1"],
-            doc["input_sentence_2"],
-            doc["input_sentence_3"],
-            doc["input_sentence_4"],
-        ])
+        return " ".join(
+            [
+                doc["input_sentence_1"],
+                doc["input_sentence_2"],
+                doc["input_sentence_3"],
+                doc["input_sentence_4"],
+            ]
+        )
 
     def doc_to_target(self, doc):
         clozes = [doc["sentence_quiz1"], doc["sentence_quiz2"]]
@@ -89,7 +93,7 @@ class StoryCloze(Task):
         return " " + clozes[doc["answer_right_ending"] - 1]
 
     def construct_requests(self, doc, ctx):
-        """ Uses RequestFactory to construct Requests and returns an iterable of
+        """Uses RequestFactory to construct Requests and returns an iterable of
         Requests which will be sent to the LM.
 
         :param doc:
@@ -100,10 +104,7 @@ class StoryCloze(Task):
             part of the document for `doc`.
         """
         clozes = [doc["sentence_quiz1"], doc["sentence_quiz2"]]
-        lls = [
-            rf.loglikelihood(ctx, " {}".format(choice))[0]
-            for choice in clozes
-        ]
+        lls = [rf.loglikelihood(ctx, " {}".format(choice))[0] for choice in clozes]
         return lls
 
     def process_results(self, doc, results):
@@ -117,10 +118,8 @@ class StoryCloze(Task):
             The results of the requests created in construct_requests.
         """
         gold = doc["answer_right_ending"] - 1
-        acc = 1. if np.argmax(results) == gold else 0.
-        return {
-            "acc": acc
-        }
+        acc = 1.0 if np.argmax(results) == gold else 0.0
+        return {"acc": acc}
 
     def aggregation(self):
         """
@@ -128,9 +127,7 @@ class StoryCloze(Task):
             A dictionary where keys are the names of submetrics and values are
             functions that aggregate a list of metrics
         """
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
     def higher_is_better(self):
         """
@@ -138,9 +135,7 @@ class StoryCloze(Task):
             A dictionary where keys are the names of submetrics and values are
             whether a higher value of the submetric is better
         """
-        return {
-            "acc": True
-        }
+        return {"acc": True}
 
 
 class StoryCloze2016(StoryCloze):

lm_eval/tasks/superglue.py

@@ -61,15 +61,15 @@ class BoolQ(Task):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return doc['passage']
-    
+        return doc["passage"]
+
     def doc_to_target(self, doc):
-        return " " + yesno(doc['label']) 
+        return " " + yesno(doc["label"])
 
     def construct_requests(self, doc, ctx):
 
-        ll_yes, _ = rf.loglikelihood(ctx, ' yes')
-        ll_no, _ = rf.loglikelihood(ctx, ' no')
+        ll_yes, _ = rf.loglikelihood(ctx, " yes")
+        ll_no, _ = rf.loglikelihood(ctx, " no")
 
         return ll_yes, ll_no
 
@@ -77,21 +77,15 @@ class BoolQ(Task):
         ll_yes, ll_no = results
         gold = doc["label"]
 
-        acc = 1. if (ll_yes > ll_no) == gold else 0.
+        acc = 1.0 if (ll_yes > ll_no) == gold else 0.0
+
+        return {"acc": acc}
 
-        return {
-            "acc": acc
-        }
-    
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
-    
+        return {"acc": True}
+
     def aggregation(self):
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
 
 class CommitmentBank(Task):
@@ -129,27 +123,21 @@ class CommitmentBank(Task):
         return " {}".format({0: "True", 1: "False", 2: "Neither"}[doc["label"]])
 
     def construct_requests(self, doc, ctx):
-        ll_true, _ = rf.loglikelihood(ctx, ' True')
-        ll_false, _ = rf.loglikelihood(ctx, ' False')
-        ll_neither, _ = rf.loglikelihood(ctx, ' Neither')
+        ll_true, _ = rf.loglikelihood(ctx, " True")
+        ll_false, _ = rf.loglikelihood(ctx, " False")
+        ll_neither, _ = rf.loglikelihood(ctx, " Neither")
 
         return ll_true, ll_false, ll_neither
 
     def process_results(self, doc, results):
         gold = doc["label"]
         pred = np.argmax(results)
-        acc = 1. if pred == gold else 0.
+        acc = 1.0 if pred == gold else 0.0
+
+        return {"acc": acc, "f1": (pred, gold)}
 
-        return {
-            "acc": acc,
-            "f1": (pred, gold)
-        }
-    
     def higher_is_better(self):
-        return {
-            "acc": True,
-            "f1": True
-        }
+        return {"acc": True, "f1": True}
 
     @classmethod
     def cb_multi_fi(cls, items):
@@ -161,7 +149,7 @@ class CommitmentBank(Task):
         f13 = sklearn.metrics.f1_score(y_true=golds == 2, y_pred=preds == 2)
         avg_f1 = mean([f11, f12, f13])
         return avg_f1
-    
+
     def aggregation(self):
         return {
             "acc": mean,
@@ -207,7 +195,7 @@ class Copa(Task):
     def construct_requests(self, doc, ctx):
         choice1 = " " + self.convert_choice(doc["choice1"])
         choice2 = " " + self.convert_choice(doc["choice2"])
-        
+
         ll_choice1, _ = rf.loglikelihood(ctx, choice1)
         ll_choice2, _ = rf.loglikelihood(ctx, choice2)
 
@@ -216,21 +204,15 @@ class Copa(Task):
     def process_results(self, doc, results):
         gold = doc["label"]
         pred = np.argmax(results)
-        acc = 1. if pred == gold else 0.
+        acc = 1.0 if pred == gold else 0.0
+
+        return {"acc": acc}
 
-        return {
-            "acc": acc
-        }
-    
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
-    
+        return {"acc": True}
+
     def aggregation(self):
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
     @staticmethod
     def convert_choice(choice):
@@ -273,28 +255,22 @@ class MultiRC(Task):
     def construct_requests(self, doc, ctx):
         true_choice = self.format_answer(answer=doc["answer"], label=True)
         false_choice = self.format_answer(answer=doc["answer"], label=False)
-        
-        ll_true_choice, _ = rf.loglikelihood(ctx, f' {true_choice}')
-        ll_false_choice, _ = rf.loglikelihood(ctx, f' {false_choice}')
+
+        ll_true_choice, _ = rf.loglikelihood(ctx, f" {true_choice}")
+        ll_false_choice, _ = rf.loglikelihood(ctx, f" {false_choice}")
 
         return ll_true_choice, ll_false_choice
 
     def process_results(self, doc, results):
         ll_true_choice, ll_false_choice = results
         pred = ll_true_choice > ll_false_choice
-        return {
-            "acc": (pred, doc)
-        }
-    
+        return {"acc": (pred, doc)}
+
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
-    
+        return {"acc": True}
+
     def aggregation(self):
-        return {
-            "acc": acc_all
-        }
+        return {"acc": acc_all}
 
 
 class ReCoRD(Task):
@@ -343,7 +319,7 @@ class ReCoRD(Task):
 
     @classmethod
     def format_answer(cls, query, entity):
-        return f'  - {query}'.replace("@placeholder", entity)
+        return f"  - {query}".replace("@placeholder", entity)
 
     def doc_to_target(self, doc):
         # We only output the first correct entity in a doc
@@ -365,8 +341,12 @@ class ReCoRD(Task):
 
         prediction = doc["entities"][max_idx]
         gold_label_set = doc["answers"]
-        f1 = metric_max_over_ground_truths(squad_metrics.compute_f1, prediction, gold_label_set)
-        em = metric_max_over_ground_truths(squad_metrics.compute_exact, prediction, gold_label_set)
+        f1 = metric_max_over_ground_truths(
+            squad_metrics.compute_f1, prediction, gold_label_set
+        )
+        em = metric_max_over_ground_truths(
+            squad_metrics.compute_exact, prediction, gold_label_set
+        )
 
         return {
             "f1": f1,
@@ -409,19 +389,21 @@ class WordsInContext(Task):
         return self.dataset["validation"]
 
     def doc_to_text(self, doc):
-        return "Sentence 1: {}\nSentence 2: {}\nQuestion: Is the word '{}' used in the same way in the" \
-               " two sentences above?\nAnswer:".format(
-                    doc["sentence1"],
-                    doc["sentence2"],
-                    doc["sentence1"][doc["start1"]:doc["end1"]],
-                )
+        return (
+            "Sentence 1: {}\nSentence 2: {}\nQuestion: Is the word '{}' used in the same way in the"
+            " two sentences above?\nAnswer:".format(
+                doc["sentence1"],
+                doc["sentence2"],
+                doc["sentence1"][doc["start1"] : doc["end1"]],
+            )
+        )
 
     def doc_to_target(self, doc):
         return " {}".format({0: "no", 1: "yes"}[doc["label"]])
 
     def construct_requests(self, doc, ctx):
-        ll_yes, _ = rf.loglikelihood(ctx, ' yes')
-        ll_no, _ = rf.loglikelihood(ctx, ' no')
+        ll_yes, _ = rf.loglikelihood(ctx, " yes")
+        ll_no, _ = rf.loglikelihood(ctx, " no")
 
         return ll_yes, ll_no
 
@@ -429,21 +411,15 @@ class WordsInContext(Task):
         ll_yes, ll_no = results
         gold = doc["label"]
 
-        acc = 1. if (ll_yes > ll_no) == gold else 0.
+        acc = 1.0 if (ll_yes > ll_no) == gold else 0.0
 
-        return {
-            "acc": acc
-        }
+        return {"acc": acc}
 
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
+        return {"acc": True}
 
     def aggregation(self):
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
 
 class SGWinogradSchemaChallenge(Task):
@@ -467,9 +443,7 @@ class SGWinogradSchemaChallenge(Task):
             if self._training_docs is None:
                 # GPT-3 Paper's format only uses positive examples for fewshot "training"
                 self._training_docs = [
-                    doc for doc in
-                    self.dataset["train"]
-                    if doc["label"]
+                    doc for doc in self.dataset["train"] if doc["label"]
                 ]
             return self._training_docs
 
@@ -479,25 +453,25 @@ class SGWinogradSchemaChallenge(Task):
     def doc_to_text(self, doc):
         raw_passage = doc["text"]
         # NOTE: HuggingFace span indices are word-based not character-based.
-        pre = " ".join(raw_passage.split()[:doc["span2_index"]])
-        post = raw_passage[len(pre) + len(doc["span2_text"]) + 1:]
-        passage = general_detokenize(pre + " *{}*".format(doc['span2_text']) + post)
+        pre = " ".join(raw_passage.split()[: doc["span2_index"]])
+        post = raw_passage[len(pre) + len(doc["span2_text"]) + 1 :]
+        passage = general_detokenize(pre + " *{}*".format(doc["span2_text"]) + post)
         noun = doc["span1_text"]
         pronoun = doc["span2_text"]
         text = (
             f"Passage: {passage}\n"
-            + f"Question: In the passage above, does the pronoun \"*{pronoun}*\" refer to \"*{noun}*\"?\n"
+            + f'Question: In the passage above, does the pronoun "*{pronoun}*" refer to "*{noun}*"?\n'
             + "Answer:"
         )
         return text
 
     def doc_to_target(self, doc):
-        return " " + yesno(doc['label'])
+        return " " + yesno(doc["label"])
 
     def construct_requests(self, doc, ctx):
 
-        ll_yes, _ = rf.loglikelihood(ctx, ' yes')
-        ll_no, _ = rf.loglikelihood(ctx, ' no')
+        ll_yes, _ = rf.loglikelihood(ctx, " yes")
+        ll_no, _ = rf.loglikelihood(ctx, " no")
 
         return ll_yes, ll_no
 
@@ -505,18 +479,12 @@ class SGWinogradSchemaChallenge(Task):
         ll_yes, ll_no = results
         gold = doc["label"]
 
-        acc = 1. if (ll_yes > ll_no) == gold else 0.
+        acc = 1.0 if (ll_yes > ll_no) == gold else 0.0
 
-        return {
-            "acc": acc
-        }
+        return {"acc": acc}
 
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
+        return {"acc": True}
 
     def aggregation(self):
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}

lm_eval/tasks/translation.py

@@ -41,44 +41,57 @@ def create_tasks_from_benchmarks(benchmark_dict):
     :return: {task_name: task}
         e.g. {wmt14-fr-en: Task, wmt16-de-en: Task}
     """
+
     def version_of(dataset, language_pair):
         if language_pair[-2:] in ["zh", "ja"]:
-            return 1 # changed to use jieba/nagisa
+            return 1  # changed to use jieba/nagisa
         return 0
 
     return {
-        f"{dataset}-{language_pair}": create_translation_task(dataset, language_pair, version_of(dataset, language_pair))
+        f"{dataset}-{language_pair}": create_translation_task(
+            dataset, language_pair, version_of(dataset, language_pair)
+        )
         for dataset, language_pairs in benchmark_dict.items()
         for language_pair in language_pairs
     }
 
+
 ########################################
 # Language Specifics
 ########################################
 
+
 def zh_split(zh_text: List[str]) -> List[str]:
     """Chinese splitting"""
     import jieba
+
     return [" ".join(jieba.cut(txt.strip())) for txt in zh_text]
 
+
 def ja_split(ja_text: List[str]) -> List[str]:
     """Japanese splitting"""
     import nagisa
+
     return [" ".join(nagisa.tagging(txt.strip()).words) for txt in ja_text]
 
+
 NO_SPACE_LANG = {"zh": zh_split, "ja": ja_split}
 
 ########################################
 # Tasks
 ########################################
 
+
 def create_translation_task(dataset, language_pair, version=0):
     class TranslationTask(GeneralTranslationTask):
         VERSION = version
+
         def __init__(self):
             super().__init__(dataset, language_pair)
+
     return TranslationTask
 
+
 class GeneralTranslationTask(Task):
     VERSION = 0
 
@@ -92,8 +105,9 @@ class GeneralTranslationTask(Task):
 
     def download(self, data_dir=None, cache_dir=None, download_mode=None):
         # This caches in the users home dir automatically
-        self.src_file, self.ref_file = \
-            sacrebleu.download_test_set(self.sacrebleu_dataset, self.sacrebleu_language_pair)
+        self.src_file, self.ref_file = sacrebleu.download_test_set(
+            self.sacrebleu_dataset, self.sacrebleu_language_pair
+        )
         self.src_data, self.ref_data = [
             [line.rstrip() for line in sacrebleu.smart_open(file)]
             for file in (self.src_file, self.ref_file)
@@ -117,10 +131,9 @@ class GeneralTranslationTask(Task):
         :return: Iterable[obj]
             A iterable of any object, that doc_to_text can handle
         """
-        return [{
-            "src": src,
-            "ref": ref
-        } for src, ref in zip(self.src_data, self.ref_data)]
+        return [
+            {"src": src, "ref": ref} for src, ref in zip(self.src_data, self.ref_data)
+        ]
 
     def doc_to_text(self, doc):
         language_codes = self.sacrebleu_language_pair.split("-")
@@ -139,7 +152,7 @@ class GeneralTranslationTask(Task):
         return " " + doc["ref"] if isinstance(doc["ref"], str) else doc["ref"][0]
 
     def construct_requests(self, doc, ctx):
-        """ Uses RequestFactory to construct Requests and returns an iterable of
+        """Uses RequestFactory to construct Requests and returns an iterable of
         Requests which will be sent to the LM.
 
         :param doc:

lm_eval/tasks/triviaqa.py

@@ -43,10 +43,10 @@ class TriviaQA(Task):
         return False
 
     def training_docs(self):
-        return self.dataset['train']
+        return self.dataset["train"]
 
     def validation_docs(self):
-        return self.dataset['validation']
+        return self.dataset["validation"]
 
     def test_docs(self):
         raise NotImplementedError()
@@ -58,10 +58,10 @@ class TriviaQA(Task):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return doc['question']
+        return doc["question"]
 
     def doc_to_target(self, doc):
-        return " " + doc['answer']['value']
+        return " " + doc["answer"]["value"]
 
     def _remove_prefixes(self, aliases):
         # Optimization: Remove any alias that has a strict prefix elsewhere in the list
@@ -75,15 +75,13 @@ class TriviaQA(Task):
 
     def construct_requests(self, doc, ctx):
         ret = []
-        for alias in self._remove_prefixes(doc['answer']['aliases']):
+        for alias in self._remove_prefixes(doc["answer"]["aliases"]):
             _, is_prediction = rf.loglikelihood(ctx, " " + alias)
             ret.append(is_prediction)
         return ret
 
     def process_results(self, doc, results):
-        return {
-            "acc": float(any(results))
-        }
+        return {"acc": float(any(results))}
 
     def aggregation(self):
         return {
@@ -91,6 +89,4 @@ class TriviaQA(Task):
         }
 
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
+        return {"acc": True}

lm_eval/tasks/truthfulqa.py

@@ -82,28 +82,29 @@ class TruthfulQAMultipleChoice(Task):
         raise NotImplementedError()
 
     def doc_to_text(self, doc):
-        return QA_PROMPT + "\n\nQ: " + doc['question'] + "\nA:"
+        return QA_PROMPT + "\n\nQ: " + doc["question"] + "\nA:"
 
     def should_decontaminate(self):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return doc['question']
+        return doc["question"]
 
     def doc_to_target(self, doc):
         return " "
 
-    def fewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None):
-        assert num_fewshot == 0, "TruthfulQA is intended only for the zero-shot setting."
+    def fewshot_context(
+        self, doc, num_fewshot, provide_description=None, rnd=None, description=None
+    ):
+        assert (
+            num_fewshot == 0
+        ), "TruthfulQA is intended only for the zero-shot setting."
         return super().fewshot_context(
-            doc=doc,
-            num_fewshot=num_fewshot,
-            rnd=rnd,
-            description=description
+            doc=doc, num_fewshot=num_fewshot, rnd=rnd, description=description
         )
 
     def construct_requests(self, doc, ctx):
-        """ Uses RequestFactory to construct Requests and returns an iterable of
+        """Uses RequestFactory to construct Requests and returns an iterable of
         Requests which will be sent to the LM.
 
         :param doc:
@@ -113,11 +114,15 @@ class TruthfulQAMultipleChoice(Task):
             language description, as well as the few shot examples, and the question
             part of the document for `doc`.
         """
+
         def get_lls(targets):
             return [rf.loglikelihood(ctx, " " + t)[0] for t in targets]
+
         # MC1 and MC2 targets are not always the same set of strings so we collect
         # likelihoods separately for simpler processing.
-        return get_lls(doc['mc1_targets']["choices"]) + get_lls(doc['mc2_targets']["choices"])
+        return get_lls(doc["mc1_targets"]["choices"]) + get_lls(
+            doc["mc2_targets"]["choices"]
+        )
 
     def process_results(self, doc, results):
         """Take a single document and the LM results and evaluates, returning a
@@ -129,37 +134,29 @@ class TruthfulQAMultipleChoice(Task):
         :param results:
             The results of the requests created in construct_requests.
         """
+
         def mc1(lls):
             # The gold answers in `mc1_targets` are always first (index = `0`).
             return np.argmax(lls) == 0
 
         def mc2(lls):
             # Split on the first `0` as everything before it is true (`1`).
-            split_idx = list(doc['mc2_targets']["labels"]).index(0)
+            split_idx = list(doc["mc2_targets"]["labels"]).index(0)
             # Compute the normalized probability mass for the correct answer.
             ll_true, ll_false = lls[:split_idx], lls[split_idx:]
             p_true, p_false = np.exp(np.array(ll_true)), np.exp(np.array(ll_false))
             p_true = p_true / (sum(p_true) + sum(p_false))
             return sum(p_true)
 
-        split_idx = len(doc['mc1_targets']["choices"])
+        split_idx = len(doc["mc1_targets"]["choices"])
         mc1_lls, mc2_lls = results[:split_idx], results[split_idx:]
-        return {
-            "mc1": mc1(mc1_lls),
-            "mc2": mc2(mc2_lls)
-        }
+        return {"mc1": mc1(mc1_lls), "mc2": mc2(mc2_lls)}
 
     def aggregation(self):
-        return {
-            "mc1": mean,
-            "mc2": mean
-        }
+        return {"mc1": mean, "mc2": mean}
 
     def higher_is_better(self):
-        return {
-            "mc1": True,
-            "mc2": True
-        }
+        return {"mc1": True, "mc2": True}
 
 
 class TruthfulQAGeneration(Task):
@@ -189,44 +186,45 @@ class TruthfulQAGeneration(Task):
             answer = answer.strip()
             if len(answer):
                 # Add a period after all answers.
-                if answer[-1] != '.':
-                    formatted_answers.append(answer + '.')
+                if answer[-1] != ".":
+                    formatted_answers.append(answer + ".")
                 else:
                     formatted_answers.append(answer)
         return formatted_answers
 
     def validation_docs(self):
         for doc in self.dataset["validation"]:
-            incorrect_answers = self._format_answers(doc['incorrect_answers'])
-            correct_answers = self._format_answers(doc['correct_answers'])
+            incorrect_answers = self._format_answers(doc["incorrect_answers"])
+            correct_answers = self._format_answers(doc["correct_answers"])
             if "I have no comment." not in correct_answers:
                 correct_answers.append("I have no comment.")
             yield {
-                'question': doc['question'].strip(),
-                'correct_answers': correct_answers,
-                'incorrect_answers': incorrect_answers
+                "question": doc["question"].strip(),
+                "correct_answers": correct_answers,
+                "incorrect_answers": incorrect_answers,
             }
 
     def test_docs(self):
         raise NotImplementedError()
 
     def doc_to_text(self, doc):
-        return QA_PROMPT + "\n\nQ: " + doc['question']
+        return QA_PROMPT + "\n\nQ: " + doc["question"]
 
     def doc_to_target(self, doc):
         return " "
 
-    def fewshot_context(self, doc, num_fewshot, provide_description=None, rnd=None, description=None):
-        assert num_fewshot == 0, "TruthfulQA is intended only for the zero-shot setting."
+    def fewshot_context(
+        self, doc, num_fewshot, provide_description=None, rnd=None, description=None
+    ):
+        assert (
+            num_fewshot == 0
+        ), "TruthfulQA is intended only for the zero-shot setting."
         return super().fewshot_context(
-            doc=doc,
-            num_fewshot=num_fewshot,
-            rnd=rnd,
-            description=description
+            doc=doc, num_fewshot=num_fewshot, rnd=rnd, description=description
         )
 
     def construct_requests(self, doc, ctx):
-        """ Uses RequestFactory to construct Requests and returns an iterable of
+        """Uses RequestFactory to construct Requests and returns an iterable of
         Requests which will be sent to the LM.
 
         :param doc:
@@ -237,7 +235,7 @@ class TruthfulQAGeneration(Task):
             part of the document for `doc`.
         """
         # TODO: Find a way to cap the number of generated tokens to `50` as in the official implementation.
-        completion = rf.greedy_until(ctx, ['.'])
+        completion = rf.greedy_until(ctx, ["."])
         return completion
 
     def process_results(self, doc, results):
@@ -251,18 +249,18 @@ class TruthfulQAGeneration(Task):
             The results of the requests created in construct_requests.
         """
         completion = results[0].strip()
-        true_refs, false_refs = doc['correct_answers'], doc['incorrect_answers']
+        true_refs, false_refs = doc["correct_answers"], doc["incorrect_answers"]
         all_refs = true_refs + false_refs
 
         # Process the sentence-level BLEURT, BLEU, and ROUGE for similarity measures.
 
         # BLEURT
         bleurt_scores_true = self.bleurt.compute(
-            predictions=[completion] * len(true_refs),
-            references=true_refs)['scores']
+            predictions=[completion] * len(true_refs), references=true_refs
+        )["scores"]
         bleurt_scores_false = self.bleurt.compute(
-            predictions=[completion] * len(false_refs),
-            references=false_refs)['scores']
+            predictions=[completion] * len(false_refs), references=false_refs
+        )["scores"]
         bleurt_correct = max(bleurt_scores_true)
         bleurt_incorrect = max(bleurt_scores_false)
         bleurt_max = bleurt_correct
@@ -271,8 +269,8 @@ class TruthfulQAGeneration(Task):
 
         # BLEU
         bleu_scores = [self.bleu([[ref]], [completion]) for ref in all_refs]
-        bleu_correct = np.nanmax(bleu_scores[:len(true_refs)])
-        bleu_incorrect = np.nanmax(bleu_scores[len(true_refs):])
+        bleu_correct = np.nanmax(bleu_scores[: len(true_refs)])
+        bleu_incorrect = np.nanmax(bleu_scores[len(true_refs) :])
         bleu_max = bleu_correct
         bleu_diff = bleu_correct - bleu_incorrect
         bleu_acc = int(bleu_correct > bleu_incorrect)
@@ -280,23 +278,23 @@ class TruthfulQAGeneration(Task):
         # ROUGE-N
         rouge_scores = [self.rouge([ref], [completion]) for ref in all_refs]
         # ROUGE-1
-        rouge1_scores = [score['rouge1'] for score in rouge_scores]
-        rouge1_correct = np.nanmax(rouge1_scores[:len(true_refs)])
-        rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs):])
+        rouge1_scores = [score["rouge1"] for score in rouge_scores]
+        rouge1_correct = np.nanmax(rouge1_scores[: len(true_refs)])
+        rouge1_incorrect = np.nanmax(rouge1_scores[len(true_refs) :])
         rouge1_max = rouge1_correct
         rouge1_diff = rouge1_correct - rouge1_incorrect
         rouge1_acc = int(rouge1_correct > rouge1_incorrect)
         # ROUGE-2
-        rouge2_scores = [score['rouge2'] for score in rouge_scores]
-        rouge2_correct = np.nanmax(rouge2_scores[:len(true_refs)])
-        rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs):])
+        rouge2_scores = [score["rouge2"] for score in rouge_scores]
+        rouge2_correct = np.nanmax(rouge2_scores[: len(true_refs)])
+        rouge2_incorrect = np.nanmax(rouge2_scores[len(true_refs) :])
         rouge2_max = rouge2_correct
         rouge2_diff = rouge2_correct - rouge2_incorrect
         rouge2_acc = int(rouge2_correct > rouge2_incorrect)
         # ROUGE-L
-        rougeL_scores = [score['rougeLsum'] for score in rouge_scores]
-        rougeL_correct = np.nanmax(rougeL_scores[:len(true_refs)])
-        rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs):])
+        rougeL_scores = [score["rougeLsum"] for score in rouge_scores]
+        rougeL_correct = np.nanmax(rougeL_scores[: len(true_refs)])
+        rougeL_incorrect = np.nanmax(rougeL_scores[len(true_refs) :])
         rougeL_max = rougeL_correct
         rougeL_diff = rougeL_correct - rougeL_incorrect
         rougeL_acc = int(rougeL_correct > rougeL_incorrect)
@@ -305,19 +303,15 @@ class TruthfulQAGeneration(Task):
             "bleurt_max": bleurt_max,
             "bleurt_acc": bleurt_acc,
             "bleurt_diff": bleurt_diff,
-
             "bleu_max": bleu_max,
             "bleu_acc": bleu_acc,
             "bleu_diff": bleu_diff,
-
             "rouge1_max": rouge1_max,
             "rouge1_acc": rouge1_acc,
             "rouge1_diff": rouge1_diff,
-
             "rouge2_max": rouge2_max,
             "rouge2_acc": rouge2_acc,
             "rouge2_diff": rouge2_diff,
-
             "rougeL_max": rougeL_max,
             "rougeL_acc": rougeL_acc,
             "rougeL_diff": rougeL_diff,
@@ -328,19 +322,15 @@ class TruthfulQAGeneration(Task):
             "bleurt_max": mean,
             "bleurt_acc": mean,
             "bleurt_diff": mean,
-
             "bleu_max": mean,
             "bleu_acc": mean,
             "bleu_diff": mean,
-
             "rouge1_max": mean,
             "rouge1_acc": mean,
             "rouge1_diff": mean,
-
             "rouge2_max": mean,
             "rouge2_acc": mean,
             "rouge2_diff": mean,
-
             "rougeL_max": mean,
             "rougeL_acc": mean,
             "rougeL_diff": mean,
@@ -351,19 +341,15 @@ class TruthfulQAGeneration(Task):
             "bleurt_max": True,
             "bleurt_acc": True,
             "bleurt_diff": True,
-
             "bleu_max": True,
             "bleu_acc": True,
             "bleu_diff": True,
-
             "rouge1_max": True,
             "rouge1_acc": True,
             "rouge1_diff": True,
-
             "rouge2_max": True,
             "rouge2_acc": True,
             "rouge2_diff": True,
-
             "rougeL_max": True,
             "rougeL_acc": True,
             "rougeL_diff": True,
@@ -387,7 +373,7 @@ class TruthfulQAGeneration(Task):
             force=False,
             lowercase=False,
             tokenize="intl",
-            use_effective_order=False
+            use_effective_order=False,
         ).score
         return score
 
@@ -404,9 +390,11 @@ class TruthfulQAGeneration(Task):
         rouge_types = ["rouge1", "rouge2", "rougeLsum"]
         scorer = rouge_scorer.RougeScorer(rouge_types)
         # Add newlines between sentences to correctly compute `rougeLsum`.
+
         def _prepare_summary(summary):
             summary = summary.replace(" . ", ".\n")
             return summary
+
         # Accumulate confidence intervals.
         aggregator = scoring.BootstrapAggregator()
         for ref, pred in zip(refs, preds):
@@ -414,4 +402,4 @@ class TruthfulQAGeneration(Task):
             pred = _prepare_summary(pred)
             aggregator.add_scores(scorer.score(ref, pred))
         result = aggregator.aggregate()
-        return {type: result[type].mid.fmeasure*100 for type in rouge_types}
+        return {type: result[type].mid.fmeasure * 100 for type in rouge_types}

lm_eval/tasks/unscramble.py

@@ -65,19 +65,13 @@ class WordUnscrambleTask(Task):
     def process_results(self, doc, results):
         pred = results[0]
         gold = doc["completion"]
-        return {
-            "acc": int(pred == gold)
-        }
+        return {"acc": int(pred == gold)}
 
     def aggregation(self):
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
+        return {"acc": True}
 
 
 class Anagrams1(WordUnscrambleTask):

lm_eval/tasks/webqs.py

@@ -54,20 +54,20 @@ class WebQs(Task):
         return self.dataset["test"]
 
     def doc_to_text(self, doc):
-        return "Question: " + doc['question'] + '\nAnswer:'
+        return "Question: " + doc["question"] + "\nAnswer:"
 
     def should_decontaminate(self):
         return True
 
     def doc_to_decontamination_query(self, doc):
-        return doc['question']
+        return doc["question"]
 
     def doc_to_target(self, doc):
-        # this picks one answer to be the "correct" one, despite sometimes 
+        # this picks one answer to be the "correct" one, despite sometimes
         # multiple correct answers being possible.
         # TODO: make sure we're actually handling multi-answer correctly
-        return " " + doc['answers'][0]
-        
+        return " " + doc["answers"][0]
+
     def _remove_prefixes(self, aliases):
         # Optimization: Remove any alias that has a strict prefix elsewhere in the list
         # we can do this because if the prefix is acceptable by isgreedy, we can stop looking
@@ -81,15 +81,13 @@ class WebQs(Task):
 
     def construct_requests(self, doc, ctx):
         ret = []
-        for alias in self._remove_prefixes(doc['answers']):
+        for alias in self._remove_prefixes(doc["answers"]):
             _, is_prediction = rf.loglikelihood(ctx, " " + alias)
             ret.append(is_prediction)
         return ret
 
     def process_results(self, doc, results):
-        return {
-            "acc": float(any(results))
-        }
+        return {"acc": float(any(results))}
 
     def aggregation(self):
         return {
@@ -97,6 +95,4 @@ class WebQs(Task):
         }
 
     def higher_is_better(self):
-        return {
-            "acc": True
-        }
+        return {"acc": True}

lm_eval/tasks/wikitext.py

@@ -2,7 +2,7 @@
 Pointer Sentinel Mixture Models
 https://arxiv.org/pdf/1609.07843.pdf
 
-The WikiText language modeling dataset is a collection of over 100 million tokens 
+The WikiText language modeling dataset is a collection of over 100 million tokens
 extracted from the set of verified Good and Featured articles on Wikipedia.
 
 NOTE: This `Task` is based on WikiText-2.
@@ -17,7 +17,7 @@ from lm_eval.base import PerplexityTask
 
 _CITATION = """
 @misc{merity2016pointer,
-    title={Pointer Sentinel Mixture Models}, 
+    title={Pointer Sentinel Mixture Models},
     author={Stephen Merity and Caiming Xiong and James Bradbury and Richard Socher},
     year={2016},
     eprint={1609.07843},

lm_eval/tasks/winogrande.py

-"""
-WinoGrande: An Adversarial Winograd Schema Challenge at Scale
-https://arxiv.org/pdf/1907.10641.pdf
-
-WinoGrande is a collection of 44k problems, inspired by Winograd Schema Challenge
-(Levesque, Davis, and Morgenstern 2011), but adjusted to improve the scale and
-robustness against the dataset-specific bias. Formulated as a fill-in-a-blank
-task with binary options, the goal is to choose the right option for a given
-sentence which requires commonsense reasoning.
-
-NOTE: This evaluation of Winogrande uses partial evaluation as described by
-Trinh & Le in Simple Method for Commonsense Reasoning (2018). 
-See: https://arxiv.org/abs/1806.02847
-
-Homepage: https://leaderboard.allenai.org/winogrande/submissions/public
-"""
-import numpy as np
-from lm_eval.base import rf, Task
-from lm_eval.metrics import mean
-
-
-_CITATION = """
-@article{sakaguchi2019winogrande,
-    title={WinoGrande: An Adversarial Winograd Schema Challenge at Scale},
-    author={Sakaguchi, Keisuke and Bras, Ronan Le and Bhagavatula, Chandra and Choi, Yejin},
-    journal={arXiv preprint arXiv:1907.10641},
-    year={2019}
-}
-"""
-
-
-class Winogrande(Task):
-    VERSION = 0
-    DATASET_PATH = "winogrande"
-    DATASET_NAME = "winogrande_xl"
-
-    answer_to_num = {'1': 0, '2': 1}
-
-    def has_training_docs(self):
-        return True
-
-    def has_validation_docs(self):
-        return True
-
-    def has_test_docs(self):
-        return False
-
-    def training_docs(self):
-        if self._training_docs is None:
-            self._training_docs = list(self.dataset["train"])
-        return self._training_docs
-
-    def validation_docs(self):
-        return self.dataset["validation"]
-
-    def doc_to_text(self, doc):
-        return self.partial_context(doc, doc["option" + doc["answer"]])
-
-    def should_decontaminate(self):
-        return True
-
-    def doc_to_decontamination_query(self, doc):
-        return doc["sentence"]
-        
-    @classmethod
-    def partial_context(cls, doc, option):
-        # Substitute the pronoun in the sentence with the specified option
-        # and ignore everything after.
-        pronoun_loc = doc["sentence"].index("_")
-        return doc["sentence"][:pronoun_loc] + option
-
-    def doc_to_target(self, doc):
-        return self.partial_target(doc)
-
-    @classmethod
-    def partial_target(cls, doc):
-        # The target is everything after the document specified pronoun.
-        pronoun_loc = doc["sentence"].index("_") + 1
-        return " " + doc["sentence"][pronoun_loc:].strip()
-
-    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`.
-        """
-        target = self.partial_target(doc)
-        lls = []
-        for option in [doc["option1"], doc["option2"]]:
-            partial_ctx = self.partial_context(doc, option)
-            full_ctx = self.append_context(ctx, partial_ctx)
-            lls.append(rf.loglikelihood(full_ctx, target)[0])
-        return lls
-
-    @classmethod
-    def append_context(cls, ctx, partial_ctx):
-        ctx = ctx.split("\n\n")  # Each fewshot context is on its own new line.
-        ctx.pop()  # Remove the correct context put in by `doc_to_text`.
-        return "\n\n".join([*ctx, partial_ctx]) if ctx else partial_ctx
-
-    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.
-        """
-        return {
-            "acc": np.argmax(results) == self.answer_to_num[doc["answer"]]
-        }
-
-    def aggregation(self):
-        """
-        :returns: {str: [float] -> float}
-            A dictionary where keys are the names of submetrics and values are
-            functions that aggregate a list of metrics
-        """
-        return {
-            "acc": mean
-        }
-
-    def higher_is_better(self):
-        """
-        :returns: {str: bool}
-            A dictionary where keys are the names of submetrics and values are
-            whether a higher value of the submetric is better
-        """
-        return {
-            "acc": True
-        }
+"""
+WinoGrande: An Adversarial Winograd Schema Challenge at Scale
+https://arxiv.org/pdf/1907.10641.pdf
+
+WinoGrande is a collection of 44k problems, inspired by Winograd Schema Challenge
+(Levesque, Davis, and Morgenstern 2011), but adjusted to improve the scale and
+robustness against the dataset-specific bias. Formulated as a fill-in-a-blank
+task with binary options, the goal is to choose the right option for a given
+sentence which requires commonsense reasoning.
+
+NOTE: This evaluation of Winogrande uses partial evaluation as described by
+Trinh & Le in Simple Method for Commonsense Reasoning (2018).
+See: https://arxiv.org/abs/1806.02847
+
+Homepage: https://leaderboard.allenai.org/winogrande/submissions/public
+"""
+import numpy as np
+from lm_eval.base import rf, Task
+from lm_eval.metrics import mean
+
+
+_CITATION = """
+@article{sakaguchi2019winogrande,
+    title={WinoGrande: An Adversarial Winograd Schema Challenge at Scale},
+    author={Sakaguchi, Keisuke and Bras, Ronan Le and Bhagavatula, Chandra and Choi, Yejin},
+    journal={arXiv preprint arXiv:1907.10641},
+    year={2019}
+}
+"""
+
+
+class Winogrande(Task):
+    VERSION = 0
+    DATASET_PATH = "winogrande"
+    DATASET_NAME = "winogrande_xl"
+
+    answer_to_num = {"1": 0, "2": 1}
+
+    def has_training_docs(self):
+        return True
+
+    def has_validation_docs(self):
+        return True
+
+    def has_test_docs(self):
+        return False
+
+    def training_docs(self):
+        if self._training_docs is None:
+            self._training_docs = list(self.dataset["train"])
+        return self._training_docs
+
+    def validation_docs(self):
+        return self.dataset["validation"]
+
+    def doc_to_text(self, doc):
+        return self.partial_context(doc, doc["option" + doc["answer"]])
+
+    def should_decontaminate(self):
+        return True
+
+    def doc_to_decontamination_query(self, doc):
+        return doc["sentence"]
+
+    @classmethod
+    def partial_context(cls, doc, option):
+        # Substitute the pronoun in the sentence with the specified option
+        # and ignore everything after.
+        pronoun_loc = doc["sentence"].index("_")
+        return doc["sentence"][:pronoun_loc] + option
+
+    def doc_to_target(self, doc):
+        return self.partial_target(doc)
+
+    @classmethod
+    def partial_target(cls, doc):
+        # The target is everything after the document specified pronoun.
+        pronoun_loc = doc["sentence"].index("_") + 1
+        return " " + doc["sentence"][pronoun_loc:].strip()
+
+    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`.
+        """
+        target = self.partial_target(doc)
+        lls = []
+        for option in [doc["option1"], doc["option2"]]:
+            partial_ctx = self.partial_context(doc, option)
+            full_ctx = self.append_context(ctx, partial_ctx)
+            lls.append(rf.loglikelihood(full_ctx, target)[0])
+        return lls
+
+    @classmethod
+    def append_context(cls, ctx, partial_ctx):
+        ctx = ctx.split("\n\n")  # Each fewshot context is on its own new line.
+        ctx.pop()  # Remove the correct context put in by `doc_to_text`.
+        return "\n\n".join([*ctx, partial_ctx]) if ctx else partial_ctx
+
+    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.
+        """
+        return {"acc": np.argmax(results) == self.answer_to_num[doc["answer"]]}
+
+    def aggregation(self):
+        """
+        :returns: {str: [float] -> float}
+            A dictionary where keys are the names of submetrics and values are
+            functions that aggregate a list of metrics
+        """
+        return {"acc": mean}
+
+    def higher_is_better(self):
+        """
+        :returns: {str: bool}
+            A dictionary where keys are the names of submetrics and values are
+            whether a higher value of the submetric is better
+        """
+        return {"acc": True}

lm_eval/tasks/wsc273.py

@@ -40,8 +40,19 @@ class WinogradSchemaChallenge273(Task):
     DATASET_PATH = "winograd_wsc"
     DATASET_NAME = "wsc273"
 
-    upper_pronouns = ["A", "An", "The", "She", "He",
-                      "It", "They", "My", "His", "Her", "Their"]
+    upper_pronouns = [
+        "A",
+        "An",
+        "The",
+        "She",
+        "He",
+        "It",
+        "They",
+        "My",
+        "His",
+        "Her",
+        "Their",
+    ]
 
     def has_training_docs(self):
         return False
@@ -68,7 +79,7 @@ class WinogradSchemaChallenge273(Task):
             option += "'s"
         # Appropriately lowercase the pronoun in the option.
         pronoun = option.split()[0]
-        start_of_sentence = doc["text"][doc['pronoun_loc'] - 2] == '.'
+        start_of_sentence = doc["text"][doc["pronoun_loc"] - 2] == "."
         if not start_of_sentence and pronoun in self.upper_pronouns:
             return option.replace(pronoun, pronoun.lower())
         return option
@@ -95,7 +106,7 @@ class WinogradSchemaChallenge273(Task):
     def partial_context(cls, doc, option):
         # Substitute the pronoun in the original text with the specified
         # option and ignore everything after.
-        return doc["text"][:doc["pronoun_loc"]] + option
+        return doc["text"][: doc["pronoun_loc"]] + option
 
     def doc_to_target(self, doc):
         return self.partial_target(doc)
@@ -141,9 +152,7 @@ class WinogradSchemaChallenge273(Task):
         :param results:
             The results of the requests created in construct_requests.
         """
-        return {
-            "acc": np.argmax(results) == doc["label"]
-        }
+        return {"acc": np.argmax(results) == doc["label"]}
 
     def aggregation(self):
         """
@@ -151,9 +160,7 @@ class WinogradSchemaChallenge273(Task):
             A dictionary where keys are the names of submetrics and values are
             functions that aggregate a list of metrics
         """
-        return {
-            "acc": mean
-        }
+        return {"acc": mean}
 
     def higher_is_better(self):
         """
@@ -161,6 +168,4 @@ class WinogradSchemaChallenge273(Task):
             A dictionary where keys are the names of submetrics and values are
             whether a higher value of the submetric is better
         """
-        return {
-            "acc": True
-        }
+        return {"acc": True}

lm_eval/utils.py

@@ -34,6 +34,7 @@ def simple_parse_args_string(args_string):
         args_dict[k] = v
     return args_dict
 
+
 def join_iters(iters):
     for iter in iters:
         yield from iter
@@ -46,23 +47,26 @@ def chunks(iter, n):
         if len(arr) == n:
             yield arr
             arr = []
-    
-    if arr: yield arr
+
+    if arr:
+        yield arr
+
 
 def group(arr, fn):
     res = collections.defaultdict(list)
 
     for ob in arr:
         res[fn(ob)].append(ob)
-    
+
     return list(res.values())
 
+
 def general_detokenize(string):
     string = string.replace(" n't", "n't")
     string = string.replace(" )", ")")
     string = string.replace("( ", "(")
-    string = string.replace("\" ", "\"")
-    string = string.replace(" \"", "\"")
+    string = string.replace('" ', '"')
+    string = string.replace(' "', '"')
     string = re.sub(r" (['.,])", r"\1", string)
     return string
 
@@ -94,10 +98,7 @@ def get_rolling_token_windows(token_list, prefix_token, max_seq_len, context_len
 
     # Special handling for first window: predict all tokens
     first_seq_len = min(max_seq_len, len(token_list))
-    yield (
-        [prefix_token] + token_list[:first_seq_len - 1],
-        token_list[:first_seq_len]
-    )
+    yield ([prefix_token] + token_list[: first_seq_len - 1], token_list[:first_seq_len])
     predicted += first_seq_len
 
     while predicted < len(token_list):
@@ -105,61 +106,66 @@ def get_rolling_token_windows(token_list, prefix_token, max_seq_len, context_len
         window_end = predicted + window_pred_len
 
         yield (
-            token_list[window_end - max_seq_len - 1:window_end - 1],
-            token_list[window_end - window_pred_len:window_end],
+            token_list[window_end - max_seq_len - 1 : window_end - 1],
+            token_list[window_end - window_pred_len : window_end],
         )
         predicted += window_pred_len
 
+
 def make_disjoint_window(pair):
-    """ Takes output from get_rolling_token_windows and makes the context not overlap with the continuation """
+    """Takes output from get_rolling_token_windows and makes the context not overlap with the continuation"""
 
     a, b = pair
 
-    return a[:-(len(b) - 1)], b
+    return a[: -(len(b) - 1)], b
+
 
 class Reorderer:
     def __init__(self, arr, fn):
         self.size = len(arr)
         arr = list(enumerate(arr))
         arr = group(arr, lambda x: fn(x[1]))
-        arr = [
-            ([y[0] for y in x], x[0][1]) for x in arr
-        ]
+        arr = [([y[0] for y in x], x[0][1]) for x in arr]
         arr.sort(key=lambda x: fn(x[1]))
 
         self.arr = arr
-        
-    
+
     def get_reordered(self):
         return [x[1] for x in self.arr]
-    
+
     def get_original(self, newarr):
         res = [None] * self.size
         cov = [False] * self.size
 
         for (inds, _), v in zip(self.arr, newarr):
-            for ind in inds: 
+            for ind in inds:
                 res[ind] = v
                 cov[ind] = True
-        
+
         assert all(cov)
-        
+
         return res
 
+
 def positional_deprecated(fn):
     """
-    A decorator to nudge users into passing only keyword args (`kwargs`) to the 
+    A decorator to nudge users into passing only keyword args (`kwargs`) to the
     wrapped function, `fn`.
     """
+
     @functools.wraps(fn)
     def _wrapper(*args, **kwargs):
-        if len(args) != 1 if inspect.ismethod(fn) else 0: 
-            print(f"WARNING: using {fn.__name__} with positional arguments is "
+        if len(args) != 1 if inspect.ismethod(fn) else 0:
+            print(
+                f"WARNING: using {fn.__name__} with positional arguments is "
                 "deprecated and will be disallowed in a future version of "
-                "lm-evaluation-harness!")
+                "lm-evaluation-harness!"
+            )
         return fn(*args, **kwargs)
+
     return _wrapper
 
+
 @positional_deprecated
 def find_test_root(start_path: pathlib.Path) -> pathlib.Path:
     """
@@ -169,12 +175,14 @@ def find_test_root(start_path: pathlib.Path) -> pathlib.Path:
     cur_path = start_path.resolve()
     max_layers = 3
     for _ in range(max_layers):
-        if (cur_path / 'tests' / 'test_version_stable.py').exists():
+        if (cur_path / "tests" / "test_version_stable.py").exists():
             return cur_path
         else:
             cur_path = cur_path.parent.resolve()
-    raise FileNotFoundError(f"Unable to find package root within {max_layers} upwards" +\
-        f"of {start_path}")
+    raise FileNotFoundError(
+        f"Unable to find package root within {max_layers} upwards" + f"of {start_path}"
+    )
+
 
 @positional_deprecated
 def run_task_tests(task_list: List[str]):
@@ -182,9 +190,16 @@ def run_task_tests(task_list: List[str]):
     Find the package root and run the tests for the given tasks
     """
     package_root = find_test_root(start_path=pathlib.Path(__file__))
-    task_string = ' or '.join(task_list)
-    args = [f'{package_root}/tests/test_version_stable.py', f'--rootdir={package_root}', '-k', f'{task_string}']
+    task_string = " or ".join(task_list)
+    args = [
+        f"{package_root}/tests/test_version_stable.py",
+        f"--rootdir={package_root}",
+        "-k",
+        f"{task_string}",
+    ]
     sys.path.append(str(package_root))
     pytest_return_val = pytest.main(args)
     if pytest_return_val:
-        raise ValueError(f"Not all tests for the specified tasks ({task_list}) ran successfully! Error code: {pytest_return_val}")
+        raise ValueError(
\ No newline at end of file
+            f"Not all tests for the specified tasks ({task_list}) ran successfully! Error code: {pytest_return_val}"
+        )

main.py

@@ -7,6 +7,7 @@ from lm_eval import tasks, evaluator
 
 logging.getLogger("openai").setLevel(logging.WARNING)
 
+
 class MultiChoice:
     def __init__(self, choices):
         self.choices = choices
@@ -23,24 +24,26 @@ class MultiChoice:
         for choice in self.choices:
             yield choice
 
+
 def parse_args():
     parser = argparse.ArgumentParser()
-    parser.add_argument('--model', required=True)
-    parser.add_argument('--model_args', default="")
-    parser.add_argument('--tasks', default=None, choices=MultiChoice(tasks.ALL_TASKS))
-    parser.add_argument('--provide_description', action="store_true")
-    parser.add_argument('--num_fewshot', type=int, default=0)
-    parser.add_argument('--batch_size', type=int, default=None)
-    parser.add_argument('--device', type=str, default=None)
-    parser.add_argument('--output_path', default=None)
-    parser.add_argument('--limit', type=int, default=None)
-    parser.add_argument('--no_cache', action="store_true")
-    parser.add_argument('--decontamination_ngrams_path', default=None)
-    parser.add_argument('--description_dict_path', default=None)  
-    parser.add_argument('--check_integrity', action="store_true")  
+    parser.add_argument("--model", required=True)
+    parser.add_argument("--model_args", default="")
+    parser.add_argument("--tasks", default=None, choices=MultiChoice(tasks.ALL_TASKS))
+    parser.add_argument("--provide_description", action="store_true")
+    parser.add_argument("--num_fewshot", type=int, default=0)
+    parser.add_argument("--batch_size", type=int, default=None)
+    parser.add_argument("--device", type=str, default=None)
+    parser.add_argument("--output_path", default=None)
+    parser.add_argument("--limit", type=int, default=None)
+    parser.add_argument("--no_cache", action="store_true")
+    parser.add_argument("--decontamination_ngrams_path", default=None)
+    parser.add_argument("--description_dict_path", default=None)
+    parser.add_argument("--check_integrity", action="store_true")
 
     return parser.parse_args()
 
+
 # Returns a list containing all values of the source_list that
 # match at least one of the patterns
 def pattern_match(patterns, source_list):
@@ -50,13 +53,16 @@ def pattern_match(patterns, source_list):
             task_names.add(matching)
     return list(task_names)
 
+
 def main():
     args = parse_args()
-        
+
     assert not args.provide_description  # not implemented
-    
+
     if args.limit:
-        print("WARNING: --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT.")
+        print(
+            "WARNING: --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT."
+        )
 
     if args.tasks is None:
         task_names = tasks.ALL_TASKS
@@ -67,7 +73,7 @@ def main():
 
     description_dict = {}
     if args.description_dict_path:
-        with open(args.description_dict_path, 'r') as f:
+        with open(args.description_dict_path, "r") as f:
             description_dict = json.load(f)
 
     results = evaluator.simple_evaluate(
@@ -81,10 +87,10 @@ def main():
         limit=args.limit,
         description_dict=description_dict,
         decontamination_ngrams_path=args.decontamination_ngrams_path,
-        check_integrity=args.check_integrity
+        check_integrity=args.check_integrity,
     )
 
-    dumped = json.dumps(results, indent=2)    
+    dumped = json.dumps(results, indent=2)
     print(dumped)
 
     if args.output_path:

pile_statistics.json

@@ -34,4 +34,4 @@
         196565318,
         203583306
     ]
-}
+}
\ No newline at end of file