Merge branch 'big-refactor' into seq2seq-refactor

lm_eval/models/textsynth.py

@@ -125,7 +125,8 @@ class TextSynthLM(LM):
         res = []
         for request in tqdm(requests):
             inp = request[0]
-            until = request[1]
+            request_args = request[1]
+            until = request_args["until"]
             response = textsynth_completion(
                 url=self.api_url + "/v1/engines/" + self.engine + "/completions",
                 headers={"Authorization": "Bearer " + self.api_key},

lm_eval/tasks/README.md

 # v1.0 Tasks
 This list keeps track of which tasks' implementations have been ported to YAML / v2.0 of the Eval Harness.
 
-Boxes should be checked iff tasks are implemented in v2.0 and tested for regression. Tasks should be struck through if checked *against original introducing paper* implementation or popularizing implementation.
+Boxes should be checked iff tasks are implemented in the refactor and tested for regression. Tasks should be struck through if checked *against original introducing paper* implementation or popularizing implementation.
 
-- [ ] Glue
-- [ ] SuperGlue
+- [ ] Glue (WIP)
+- [x] SuperGlue
 - [ ] CoQA
 - [ ] DROP
 - [x] ~~Lambada~~
@@ -31,7 +31,7 @@ Boxes should be checked iff tasks are implemented in v2.0 and tested for regress
 - [ ] WebQs
 - [ ] WSC273
 - [ ] Winogrande
-- [ ] ANLI
+- [x] ANLI
 - [ ] Hendrycks Ethics
 - [ ] TruthfulQA
 - [ ] MuTual

lm_eval/tasks/__init__.py

 import os
 from typing import List, Union
 
-from .gsm8k import *
-from .triviaqa import *
-
 from lm_eval import utils
 from lm_eval.logger import eval_logger
 from lm_eval.api.task import TaskConfig, Task, ConfigurableTask
@@ -12,6 +9,7 @@ from lm_eval.api.registry import (
     register_group,
     TASK_REGISTRY,
     GROUP_REGISTRY,
+    ALL_TASKS,
 )
 
 
@@ -19,37 +17,45 @@ def get_task_name_from_config(task_config):
     return "{dataset_path}_{dataset_name}".format(**task_config)
 
 
+def include_task_folder(task_dir):
+    """
+    Calling this function
+    """
+    for root, subdirs, file_list in os.walk(task_dir):
+        if (subdirs == []) and (len(file_list) > 0):
+            for f in file_list:
+                if f.endswith(".yaml"):
+                    yaml_path = os.path.join(root, f)
+                    try:
+                        config = utils.load_yaml_config(yaml_path)
+
+                        SubClass = type(
+                            config["task"] + "ConfigurableTask",
+                            (ConfigurableTask,),
+                            {"CONFIG": TaskConfig(**config)},
+                        )
+
+                        if "task" in config:
+                            # task_name = "{}:{}".format(
+                            #     get_task_name_from_config(config), config["task"]
+                            # )
+                            task_name = "{}".format(config["task"])
+                            register_task(task_name)(SubClass)
+
+                        if "group" in config:
+                            for group in config["group"]:
+                                register_group(group)(SubClass)
+                    except Exception as error:
+                        eval_logger.warning(
+                            "Failed to load config in\n"
+                            f"                                 {yaml_path}\n"
+                            "                                 Config will not be added to registry\n"
+                            f"                                 Error: {error}"
+                        )
+
+
 task_dir = os.path.dirname(os.path.abspath(__file__)) + "/"
-for root, subdirs, file_list in os.walk(task_dir):
-    if (subdirs == []) and (len(file_list) > 0):
-        for file in file_list:
-            if "yaml" in file:
-                yaml_path = os.path.join(root, file)
-                try:
-                    config = utils.load_yaml_config(yaml_path)
-
-                    SubClass = type(
-                        config["task"] + "ConfigurableTask",
-                        (ConfigurableTask,),
-                        {"CONFIG": TaskConfig(**config)},
-                    )
-
-                    if "task" in config:
-                        task_name = "{}".format(config["task"])
-                        register_task(task_name)(SubClass)
-
-                    if "group" in config:
-                        for group in config["group"]:
-                            register_group(group)(SubClass)
-                except Exception as error:
-                    eval_logger.warning(
-                        "Failed to load config in\n"
-                        f"                                 {yaml_path}\n"
-                        "                                 Config will not be added to registry"
-                        f"                                 Error: {error}"
-                    )
-
-ALL_TASKS = sorted(list(TASK_REGISTRY.keys()) + list(GROUP_REGISTRY.keys()))
+include_task_folder(task_dir)
 
 
 def get_task(task_name, config):
@@ -57,7 +63,7 @@ def get_task(task_name, config):
         return TASK_REGISTRY[task_name](config=config)
     except KeyError:
         eval_logger.info("Available tasks:")
-        eval_logger.info(ALL_TASKS)
+        eval_logger.info(list(TASK_REGISTRY) + list(GROUP_REGISTRY))
         raise KeyError(f"Missing task {task_name}")
 
 

lm_eval/tasks/arc.py

-"""
-Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
-https://arxiv.org/pdf/1803.05457.pdf
-
-The ARC dataset consists of 7,787 science exam questions drawn from a variety
-of sources, including science questions provided under license by a research
-partner affiliated with AI2. These are text-only, English language exam questions
-that span several grade levels as indicated in the files. Each question has a
-multiple choice structure (typically 4 answer options). The questions are sorted
-into a Challenge Set of 2,590 “hard” questions (those that both a retrieval and
-a co-occurrence method fail to answer correctly) and an Easy Set of 5,197 questions.
-
-Homepage: https://allenai.org/data/arc
-"""
-from lm_eval import utils
-from lm_eval.prompts import get_prompt
-from lm_eval.api.task import MultipleChoiceTask
-
-from lm_eval.api.registry import register_task, register_group
-
-_CITATION = """
-@article{Clark2018ThinkYH,
-  title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
-  author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
-  journal={ArXiv},
-  year={2018},
-  volume={abs/1803.05457}
-}
-"""
-
-
-@register_group("arc")
-@register_task("arc_easy")
-class ARCEasy(MultipleChoiceTask):
-    VERSION = "2.0"
-    DATASET_PATH = "ai2_arc"
-    DATASET_NAME = "ARC-Easy"
-
-    OUTPUT_TYPE = "loglikelihood"
-
-    def has_training_docs(self):
-        return True
-
-    def has_validation_docs(self):
-        return True
-
-    def has_test_docs(self):
-        return True
-
-    def training_docs(self):
-        if self._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):
-        return map(self._process_doc, self.dataset["test"])
-
-    def _process_doc(self, doc):
-        # NOTE: Some `doc["answerKey"]`s are in numeric string format being one
-        # of {'1', '2', '3', '4', '5'}. We map them back to letters.
-        num_to_letter = {"1": "A", "2": "B", "3": "C", "4": "D", "5": "E"}
-        doc["answerKey"] = num_to_letter.get(doc["answerKey"], doc["answerKey"])
-        out_doc = {
-            "id": doc["id"],
-            "question": doc["question"],
-            "choices": doc["choices"]["text"],
-            "gold": ["A", "B", "C", "D", "E"].index(doc["answerKey"]),
-        }
-        return out_doc
-
-    def doc_to_text(self, doc):
-        doc_to_text = get_prompt("qa-basic:question-newline-answer")
-        return utils.apply_template(doc_to_text, doc)
-
-    def should_decontaminate(self):
-        return True
-
-    def doc_to_decontamination_query(self, doc):
-        return doc["query"]
-
-
-@register_group("arc")
-@register_task("arc_challenge")
-class ARCChallenge(ARCEasy):
-    DATASET_PATH = "ai2_arc"
-    DATASET_NAME = "ARC-Challenge"

lm_eval/tasks/arc/arc_challenge.yaml

 group:
-  - arc_yaml
-task: arc_challenge_yaml
+  - ai2_arc
+  - multiple_choice
+task: arc_challenge
 dataset_path: ai2_arc
 dataset_name: ARC-Challenge
 output_type: multiple_choice

lm_eval/tasks/arc/arc_easy.yaml

 group:
-  - arc_yaml
-task: arc_easy_yaml
+  - ai2_arc
+  - multiple_choice
+task: arc_easy
 dataset_path: ai2_arc
 dataset_name: ARC-Easy
 output_type: multiple_choice

lm_eval/tasks/gsm8k.py

-"""
-"Training Verifiers to Solve Math Word Problems"
-https://arxiv.org/abs/2110.14168
-
-State-of-the-art language models can match human performance on many tasks, but
-they still struggle to robustly perform multi-step mathematical reasoning. To
-diagnose the failures of current models and support research, we introduce GSM8K,
-a dataset of 8.5K high quality linguistically diverse grade school math word problems.
-We find that even the largest transformer models fail to achieve high test performance,
-despite the conceptual simplicity of this problem distribution.
-
-NOTE: See the official implementation of the task:
-    https://github.com/openai/grade-school-math/blob/master/grade_school_math/calculator.py
-for how to make use of the dataset's calculator annotations in your language
-model's sample/generation function.
-
-Homepage: https://github.com/openai/grade-school-math
-"""
-import re
-from lm_eval import utils
-from lm_eval.api.task import Task
-from lm_eval.api.metrics import mean
-from lm_eval.api.instance import Instance
-
-from lm_eval.prompts import get_prompt
-
-from lm_eval.api.registry import register_task, register_group
-
-_CITATION = """
-@misc{cobbe2021training,
-      title={Training Verifiers to Solve Math Word Problems},
-      author={Karl Cobbe and Vineet Kosaraju and Mohammad Bavarian and Jacob Hilton and Reiichiro Nakano and Christopher Hesse and John Schulman},
-      year={2021},
-      eprint={2110.14168},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG}
-}
-"""
-
-
-ANS_RE = re.compile(r"#### (\-?[0-9\.\,]+)")
-INVALID_ANS = "[invalid]"
-
-
-@register_task("gsm8k")
-class GradeSchoolMath8K(Task):
-    VERSION = 0
-    DATASET_PATH = "gsm8k"
-    DATASET_NAME = "main"
-
-    OUTPUT_TYPE = "greedy_until"
-
-    def has_training_docs(self):
-        return True
-
-    def has_validation_docs(self):
-        return False
-
-    def has_test_docs(self):
-        return True
-
-    def training_docs(self):
-        return self.dataset["train"]
-
-    def validation_docs(self):
-        raise NotImplementedError
-
-    def test_docs(self):
-        return self.dataset["test"]
-
-    def doc_to_text(self, doc):
-        doc_to_text = get_prompt("qa-basic:question-newline-answer")
-        return utils.apply_template(doc_to_text, doc)
-        # return "Question: " + doc["question"] + "\nAnswer:"
-
-    def doc_to_target(self, doc):
-        return " " + doc["answer"]
-
-    def construct_requests(self, doc, ctx, **kwargs):
-        """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`.
-        """
-        # NOTE: The paper implements "verifiers" that assign a score to multiple
-        # solutions and output the highest ranked solution.
-        return Instance(
-            request_type=self.OUTPUT_TYPE,
-            doc=doc,
-            arguments=(ctx, ["\n\n"]),
-            idx=0,
-            **kwargs
-        )
-        # completion = rf.greedy_until(ctx, ["\n"])
-        # return completion
-
-    def _extract_answer(self, completion):
-        match = ANS_RE.search(completion)
-        if match:
-            match_str = match.group(1).strip()
-            match_str = match_str.replace(",", "")
-            return match_str
-        else:
-            return INVALID_ANS
-
-    def _is_correct(self, completion, answer):
-        gold = self._extract_answer(answer)
-        assert gold != INVALID_ANS, "No ground truth answer found in the document."
-        # return self._extract_answer(completion) == gold
-        # print(completion)
-        return self._extract_answer(completion) == gold
-
-    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.
-        """
-
-        completion = results[0]
-        answer = doc["answer"]
-        return {"acc": self._is_correct(completion, 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/gsm8k/README.md

@@ -30,3 +30,17 @@ Homepage: https://github.com/openai/grade-school-math
       primaryClass={cs.LG}
 }
 ```
+
+
+### Checklist
+
+- [x] Is in Eval-harness v1.0 ?
+- [ ] Has been checked for regression from v1.0?
+- [ ] Has been checked for equivalence with original paper methodology?
+- [ ] "Main" checked variant clearly denoted?
+
+### Variant Wishlist
+
+- [ ] Variant with Calculator (see https://github.com/openai/grade-school-math/blob/master/grade_school_math/calculator.py for example implementation)
+- [ ] Using Verifiers
+- [ ] Majority voting "without CoT"

lm_eval/tasks/gsm8k/gsm8k-cot-self-consistency.yaml

@@ -9,7 +9,7 @@ generation_kwargs:
     - "\n\n"
   do_sample: true
   temperature: 0.2
-repeats: 8
+repeats: 64
 filter_list:
   - name: "score-first" # pick only the first response, and report metrics on that
     filter:

lm_eval/tasks/gsm8k/gsm8k.yaml

+group:
+  - greedy_until
+  - math_word_problems
 task: gsm8k_yaml
 dataset_path: gsm8k
 dataset_name: main
@@ -25,7 +28,7 @@ generation_kwargs:
     - "Question:"
   do_sample: false
   temperature: 0.0
-repeats: 2
+repeats: 1
 num_fewshot: 5
 # filter_list:
 #   - name: "get-answer"

lm_eval/tasks/lambada.py

-"""
-The LAMBADA dataset: Word prediction requiring a broad discourse context∗
-https://arxiv.org/pdf/1606.06031.pdf
-
-LAMBADA is a dataset to evaluate the capabilities of computational models for text
-understanding by means of a word prediction task. LAMBADA is a collection of narrative
-passages sharing the characteristic that human subjects are able to guess their last
-word if they are exposed to the whole passage, but not if they only see the last
-sentence preceding the target word. To succeed on LAMBADA, computational models
-cannot simply rely on local context, but must be able to keep track of information
-in the broader discourse.
-
-Homepage: https://zenodo.org/record/2630551#.X4Xzn5NKjUI
-"""
-from lm_eval.api.task import Task
-from lm_eval.api.instance import Instance
-from lm_eval.api.metrics import mean, perplexity
-
-from lm_eval.api.registry import register_task, register_group
-
-_CITATION = """
-@misc{
-    author={Paperno, Denis and Kruszewski, Germán and Lazaridou, Angeliki and Pham, Quan Ngoc and Bernardi, Raffaella and Pezzelle, Sandro and Baroni, Marco and Boleda, Gemma and Fernández, Raquel},
-    title={The LAMBADA dataset},
-    DOI={10.5281/zenodo.2630551},
-    publisher={Zenodo},
-    year={2016},
-    month={Aug}
-}
-"""
-
-
-class LambadaBase(Task):
-    VERSION = None
-
-    OUTPUT_TYPE = "loglikelihood"
-
-    def training_docs(self):
-        if self.has_training_docs():
-            return self.dataset["train"]
-
-    def validation_docs(self):
-        if self.has_validation_docs():
-            return self.dataset["validation"]
-
-    def test_docs(self):
-        if self.has_test_docs():
-            return self.dataset["test"]
-
-    def doc_to_text(self, doc):
-        return doc["text"].rsplit(" ", 1)[0]
-
-    def should_decontaminate(self):
-        return True
-
-    def doc_to_decontamination_query(self, doc):
-        return doc["text"]
-
-    def doc_to_target(self, doc):
-        return " " + doc["text"].rsplit(" ", 1)[1]
-
-    def construct_requests(self, doc, ctx, **kwargs):
-        return Instance(
-            request_type=self.OUTPUT_TYPE,
-            doc=doc,
-            arguments=(ctx, self.doc_to_target(doc)),
-            **kwargs
-        )
-
-    def process_results(self, doc, results):
-        # TODO: this ^ is a hack. filters should make it so that we only have one response per request that we score
-        results = results[
-            0
-        ]  # TODO: recheck this. currently a list of [(ll, is_greedy)] is passed in
-        ll, is_greedy = results
-
-        return {"ppl": ll, "acc": int(is_greedy)}
-
-    def aggregation(self):
-        return {"ppl": perplexity, "acc": mean}
-
-    def higher_is_better(self):
-        return {"ppl": False, "acc": True}
-
-
-@register_task("lambada_standard")
-class LambadaStandard(LambadaBase):
-    """The LAMBADA task using the standard original LAMBADA dataset."""
-
-    VERSION = "2.0"
-    DATASET_PATH = "lambada"
-
-    def has_training_docs(self):
-        return False
-
-    def has_validation_docs(self):
-        return True
-
-    def has_test_docs(self):
-        return True
-
-
-@register_task("lambada_openai")
-class LambadaOpenAI(LambadaBase):
-    """The LAMBADA task using the LAMBADA OpenAI dataset, a modified version of the
-    original LAMBADA dataset created by OpenAI for evaluating their GPT-2 model.
-
-    Reference: https://github.com/openai/gpt-2/issues/131#issuecomment-497136199
-    """
-
-    VERSION = "2.0"
-    DATASET_PATH = "EleutherAI/lambada_openai"
-
-    def has_training_docs(self):
-        return False
-
-    def has_validation_docs(self):
-        return False
-
-    def has_test_docs(self):
-        return True

lm_eval/tasks/lambada/lambada_openai.yaml

 group:
   - lambada
-task: lambada_openai_yaml
+  - loglikelihood
+  - perplexity
+task: lambada_openai
 dataset_path: EleutherAI/lambada_openai
 dataset_name: default
 output_type: loglikelihood

lm_eval/tasks/lambada/lambada_standard.yaml

 group:
   - lambada
-task: lambada_standard_yaml
+  - loglikelihood
+  - perplexity
+task: lambada_standard
 dataset_path: lambada
 dataset_name: null
 output_type: loglikelihood

lm_eval/tasks/lambada_cloze/lambada_openai_cloze.yaml

 group:
   - lambada_cloze
+  - loglikelihood
 task: lambada_openai_cloze_yaml
 dataset_path: EleutherAI/lambada_openai
 dataset_name: default

lm_eval/tasks/lambada_cloze/lambada_standard_cloze.yaml

 group:
   - lambada_cloze
+  - loglikelihood
 task: lambada_standard_cloze_yaml
 dataset_path: lambada
 dataset_name: null
@@ -15,6 +16,6 @@ metric_list:
   - metric: perplexity
     aggregation: perplexity
     higher_is_better: false
-  - metric: accuracy
+  - metric: acc
     aggregation: mean
     higher_is_better: true

lm_eval/tasks/pile.py

-"""
-The Pile: An 800GB Dataset of Diverse Text for Language Modeling
-https://arxiv.org/pdf/2101.00027.pdf
-
-The Pile is a 825 GiB diverse, open source language modelling data set that consists
-of 22 smaller, high-quality datasets combined together. To score well on Pile
-BPB (bits per byte), a model must be able to understand many disparate domains
-including books, github repositories, webpages, chat logs, and medical, physics,
-math, computer science, and philosophy papers.
-Homepage: https://pile.eleuther.ai/
-"""
-
-from lm_eval.api.task import PerplexityTask
-
-from lm_eval.api.registry import register_task, register_group
-
-_CITATION = """
-@article{pile,
-  title={The {P}ile: An 800GB Dataset of Diverse Text for Language Modeling},
-  author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and Presser, Shawn and Leahy, Connor},
-  journal={arXiv preprint arXiv:2101.00027},
-  year={2020}
-}
-"""
-
-
-class PilePerplexityTask(PerplexityTask):
-    VERSION = "2.0"
-    DATASET_PATH = "EleutherAI/the_pile"
-    DATASET_NAME = None
-
-    def has_training_docs(self):
-        return False
-
-    def test_docs(self):
-        for doc in self.dataset["train"].select(range(100)):
-            yield doc
-
-    def has_validation_docs(self):
-        return False
-
-    def has_test_docs(self):
-        return True
-
-    def doc_to_target(self, doc):
-        return doc["text"]
-
-    # def validation_docs(self):
-    #     for doc in self.dataset["validation"]:
-    #         yield doc["text"]
-
-    # def test_docs(self):
-    #     for doc in self.dataset["test"]:
-    #         yield doc["text"]
-
-
-class PileArxiv(PilePerplexityTask):
-    DATASET_NAME = "pile_arxiv"
-
-
-class PileBooks3(PilePerplexityTask):
-    DATASET_NAME = "pile_books3"
-
-
-class PileBookCorpus2(PilePerplexityTask):
-    DATASET_NAME = "pile_bookcorpus2"
-
-
-class PileDmMathematics(PilePerplexityTask):
-    DATASET_NAME = "pile_dm-mathematics"
-
-
-@register_task("pile_enron")
-class PileEnron(PilePerplexityTask):
-    DATASET_NAME = "enron_emails"
-
-
-class PileEuroparl(PilePerplexityTask):
-    DATASET_NAME = "pile_europarl"
-
-
-class PileFreeLaw(PilePerplexityTask):
-    DATASET_NAME = "pile_freelaw"
-
-
-class PileGithub(PilePerplexityTask):
-    DATASET_NAME = "pile_github"
-
-
-class PileGutenberg(PilePerplexityTask):
-    DATASET_NAME = "pile_gutenberg"
-
-
-class PileHackernews(PilePerplexityTask):
-    DATASET_NAME = "pile_hackernews"
-
-
-class PileNIHExporter(PilePerplexityTask):
-    DATASET_NAME = "pile_nih-exporter"
-
-
-class PileOpenSubtitles(PilePerplexityTask):
-    DATASET_NAME = "pile_opensubtitles"
-
-
-class PileOpenWebText2(PilePerplexityTask):
-    DATASET_NAME = "pile_openwebtext2"
-
-
-class PilePhilPapers(PilePerplexityTask):
-    DATASET_NAME = "pile_philpapers"
-
-
-class PilePileCc(PilePerplexityTask):
-    DATASET_NAME = "pile_pile-cc"
-
-
-class PilePubmedAbstracts(PilePerplexityTask):
-    DATASET_NAME = "pile_pubmed-abstracts"
-
-
-class PilePubmedCentral(PilePerplexityTask):
-    DATASET_NAME = "pile_pubmed-central"
-
-
-class PileStackExchange(PilePerplexityTask):
-    DATASET_NAME = "pile_stackexchange"
-
-
-class PileUspto(PilePerplexityTask):
-    DATASET_NAME = "pile_upsto"
-
-
-class PileUbuntuIrc(PilePerplexityTask):
-    DATASET_NAME = "pile_ubuntu-irc"
-
-
-class PileWikipedia(PilePerplexityTask):
-    DATASET_NAME = "pile_wikipedia"
-
-
-class PileYoutubeSubtitles(PilePerplexityTask):
-    DATASET_NAME = "pile_youtubesubtitles"

lm_eval/tasks/pile/pile_arxiv.yaml

 group:
   - pile
+  - perplexity
+  - loglikelihood_rolling
 task: pile_arxiv
 dataset_path: EleutherAI/the_pile
 dataset_name: pile_arxiv

lm_eval/tasks/pile/pile_bookcorpus2.yaml

-group:
-  - pile
+include: pile_arxiv.yaml
 task: pile_bookcorpus2
-dataset_path: EleutherAI/the_pile
 dataset_name: pile_bookcorpus2
-output_type: loglikelihood_rolling
-test_split: train
-template_aliases: ""
-doc_to_text: ""
-doc_to_target: "{{text}}"
-should_decontaminate: true
-doc_to_decontamination_query: "{{text}}"
-metric_list:
-  - metric: word_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: byte_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: bits_per_byte
-    aggregation: bits_per_byte
-    higher_is_better: false

lm_eval/tasks/pile/pile_books3.yaml

-group:
-  - pile
+include: pile_arxiv.yaml
 task: pile_books3
-dataset_path: EleutherAI/the_pile
 dataset_name: pile_books3
-output_type: loglikelihood_rolling
-test_split: train
-template_aliases: ""
-doc_to_text: ""
-doc_to_target: "{{text}}"
-should_decontaminate: true
-doc_to_decontamination_query: "{{text}}"
-metric_list:
-  - metric: word_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: byte_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: bits_per_byte
-    aggregation: bits_per_byte
-    higher_is_better: false

lm_eval/tasks/pile/pile_dm-mathematics.yaml

-group:
-  - pile
+include: pile_arxiv.yaml
 task: pile_dm-mathematics
-dataset_path: EleutherAI/the_pile
 dataset_name: pile_dm-mathematics
-output_type: loglikelihood_rolling
-test_split: train
-template_aliases: ""
-doc_to_text: ""
-doc_to_target: "{{text}}"
-should_decontaminate: true
-doc_to_decontamination_query: "{{text}}"
-metric_list:
-  - metric: word_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: byte_perplexity
-    aggregation: weighted_perplexity
-    higher_is_better: false
-  - metric: bits_per_byte
-    aggregation: bits_per_byte
-    higher_is_better: false