fix for merge from master

lm_eval/datasets/mutual/dataset_infos.json

-{"mutual": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nThe MuTual dataset.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 5141602, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 634396, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 624271, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6400269, "size_in_bytes": 17398147}, "mutual_plus": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nMuTualPlus is a more difficult MuTual that replaces positive responses with a safe responses.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual_plus", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 4921179, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 606620, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 597340, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6125139, "size_in_bytes": 17123017}}
+{"mutual": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nThe MuTual dataset.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 5141602, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 634396, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 624271, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6400269, "size_in_bytes": 17398147}, "mutual_plus": {"description": "MuTual is a retrieval-based dataset for multi-turn dialogue reasoning, which is\nmodified from Chinese high school English listening comprehension test data.\n\nMuTualPlus is a more difficult MuTual that replaces positive responses with a safe responses.", "citation": "@inproceedings{mutual,\n    title = \"MuTual: A Dataset for Multi-Turn Dialogue Reasoning\",\n    author = \"Cui, Leyang  and Wu, Yu and Liu, Shujie and Zhang, Yue and Zhou, Ming\" ,\n    booktitle = \"Proceedings of the 58th Conference of the Association for Computational Linguistics\",\n    year = \"2020\",\n    publisher = \"Association for Computational Linguistics\",\n}\n", "homepage": "https://github.com/Nealcly/MuTual", "license": "", "features": {"answers": {"dtype": "string", "id": null, "_type": "Value"}, "options": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "article": {"dtype": "string", "id": null, "_type": "Value"}, "id": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "mutual", "config_name": "mutual_plus", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 4921179, "num_examples": 7088, "dataset_name": "mutual"}, "test": {"name": "test", "num_bytes": 606620, "num_examples": 886, "dataset_name": "mutual"}, "validation": {"name": "validation", "num_bytes": 597340, "num_examples": 886, "dataset_name": "mutual"}}, "download_checksums": {"https://github.com/Nealcly/MuTual/archive/master.zip": {"num_bytes": 10997878, "checksum": "bb325cf6c672f0f02699993a37138b0fa0af6fcfc77ec81dfbe46add4d7b29f9"}}, "download_size": 10997878, "post_processing_size": null, "dataset_size": 6125139, "size_in_bytes": 17123017}}
\ No newline at end of file

lm_eval/datasets/pile/pile.py

@@ -42,8 +42,8 @@ _HOMEPAGE = "https://pile.eleuther.ai/"
 _LICENSE = ""
 
 _URLS = {
-    "validation": "http://eaidata.bmk.sh/data/pile/val.jsonl.zst",
-    "test": "http://eaidata.bmk.sh/data/pile/test.jsonl.zst",
+    "validation": "https://the-eye.eu/public/AI/pile/val.jsonl.zst",
+    "test": "https://the-eye.eu/public/AI/pile/test.jsonl.zst",
 }
 
 _NAMES = {
@@ -103,10 +103,7 @@ class Pile(datasets.GeneratorBasedBuilder):
             datasets.SplitGenerator(
                 name=datasets.Split.TEST,
                 # These kwargs will be passed to _generate_examples
-                gen_kwargs={
-                    "filepath": data_dir["test"],
-                    "split": "test"
-                },
+                gen_kwargs={"filepath": data_dir["test"], "split": "test"},
             ),
             datasets.SplitGenerator(
                 name=datasets.Split.VALIDATION,

lm_eval/datasets/quac/dataset_infos.json

-{"quac": {"description": "Question Answering in Context (QuAC) is a dataset for modeling, understanding, and \nparticipating in information seeking dialog. Data instances consist of an interactive\ndialog between two crowd workers: (1) a student who poses a sequence of freeform\nquestions to learn as much as possible about a hidden Wikipedia text, and (2)\na teacher who answers the questions by providing short excerpts (spans) from the text.\n", "citation": "@article{choi2018quac,\n    title={Quac: Question answering in context},\n    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},\n    journal={arXiv preprint arXiv:1808.07036},\n    year={2018}\n}\n", "homepage": "https://quac.ai/", "license": "", "features": {"title": {"dtype": "string", "id": null, "_type": "Value"}, "section_title": {"dtype": "string", "id": null, "_type": "Value"}, "paragraph": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "quac", "config_name": "quac", "version": {"version_str": "1.1.0", "description": null, "major": 1, "minor": 1, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 212391958, "num_examples": 83568, "dataset_name": "quac"}, "validation": {"name": "validation", "num_bytes": 20678483, "num_examples": 7354, "dataset_name": "quac"}}, "download_checksums": {"https://s3.amazonaws.com/my89public/quac/train_v0.2.json": {"num_bytes": 68114819, "checksum": "ff5cca5a2e4b4d1cb5b5ced68b9fce88394ef6d93117426d6d4baafbcc05c56a"}, "https://s3.amazonaws.com/my89public/quac/val_v0.2.json": {"num_bytes": 8929167, "checksum": "09e622916280ba04c9352acb1bc5bbe80f11a2598f6f34e934c51d9e6570f378"}}, "download_size": 77043986, "post_processing_size": null, "dataset_size": 233070441, "size_in_bytes": 310114427}}
+{"quac": {"description": "Question Answering in Context (QuAC) is a dataset for modeling, understanding, and \nparticipating in information seeking dialog. Data instances consist of an interactive\ndialog between two crowd workers: (1) a student who poses a sequence of freeform\nquestions to learn as much as possible about a hidden Wikipedia text, and (2)\na teacher who answers the questions by providing short excerpts (spans) from the text.\n", "citation": "@article{choi2018quac,\n    title={Quac: Question answering in context},\n    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},\n    journal={arXiv preprint arXiv:1808.07036},\n    year={2018}\n}\n", "homepage": "https://quac.ai/", "license": "", "features": {"title": {"dtype": "string", "id": null, "_type": "Value"}, "section_title": {"dtype": "string", "id": null, "_type": "Value"}, "paragraph": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "quac", "config_name": "quac", "version": {"version_str": "1.1.0", "description": null, "major": 1, "minor": 1, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 212391958, "num_examples": 83568, "dataset_name": "quac"}, "validation": {"name": "validation", "num_bytes": 20678483, "num_examples": 7354, "dataset_name": "quac"}}, "download_checksums": {"https://s3.amazonaws.com/my89public/quac/train_v0.2.json": {"num_bytes": 68114819, "checksum": "ff5cca5a2e4b4d1cb5b5ced68b9fce88394ef6d93117426d6d4baafbcc05c56a"}, "https://s3.amazonaws.com/my89public/quac/val_v0.2.json": {"num_bytes": 8929167, "checksum": "09e622916280ba04c9352acb1bc5bbe80f11a2598f6f34e934c51d9e6570f378"}}, "download_size": 77043986, "post_processing_size": null, "dataset_size": 233070441, "size_in_bytes": 310114427}}
\ No newline at end of file

lm_eval/datasets/triviaqa/dataset_infos.json

-{"triviaqa": {"description": "TriviaQA is a reading comprehension dataset containing over 650K question-answer-evidence\ntriples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts\nand independently gathered evidence documents, six per question on average, that provide\nhigh quality distant supervision for answering the questions.\n", "citation": "@InProceedings{JoshiTriviaQA2017,\n    author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel S. and Zettlemoyer, Luke},\n    title = {TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension},\n    booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics},\n    month = {July},\n    year = {2017},\n    address = {Vancouver, Canada},\n    publisher = {Association for Computational Linguistics},\n}\n", "homepage": "https://nlp.cs.washington.edu/triviaqa/", "license": "", "features": {"question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"aliases": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "values": {"dtype": "string", "id": null, "_type": "Value"}}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "trivia_qa", "config_name": "triviaqa", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 32846960, "num_examples": 87622, "dataset_name": "trivia_qa"}, "validation": {"name": "validation", "num_bytes": 4316214, "num_examples": 11313, "dataset_name": "trivia_qa"}}, "download_checksums": {"http://eaidata.bmk.sh/data/triviaqa-unfiltered.tar.gz": {"num_bytes": 546481381, "checksum": "adc19b42769062d241a8fbe834c56e58598d9322eb6c614e9f33a68a2cf5523e"}}, "download_size": 546481381, "post_processing_size": null, "dataset_size": 37163174, "size_in_bytes": 583644555}}
+{"triviaqa": {"description": "TriviaQA is a reading comprehension dataset containing over 650K question-answer-evidence\ntriples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts\nand independently gathered evidence documents, six per question on average, that provide\nhigh quality distant supervision for answering the questions.\n", "citation": "@InProceedings{JoshiTriviaQA2017,\n    author = {Joshi, Mandar and Choi, Eunsol and Weld, Daniel S. and Zettlemoyer, Luke},\n    title = {TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension},\n    booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics},\n    month = {July},\n    year = {2017},\n    address = {Vancouver, Canada},\n    publisher = {Association for Computational Linguistics},\n}\n", "homepage": "https://nlp.cs.washington.edu/triviaqa/", "license": "Apache License 2.0", "features": {"question_id": {"dtype": "string", "id": null, "_type": "Value"}, "question_source": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "answer": {"aliases": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "value": {"dtype": "string", "id": null, "_type": "Value"}}, "search_results": {"feature": {"description": {"dtype": "string", "id": null, "_type": "Value"}, "filename": {"dtype": "string", "id": null, "_type": "Value"}, "rank": {"dtype": "int32", "id": null, "_type": "Value"}, "title": {"dtype": "string", "id": null, "_type": "Value"}, "url": {"dtype": "string", "id": null, "_type": "Value"}, "search_context": {"dtype": "string", "id": null, "_type": "Value"}}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "triviaqa", "config_name": "triviaqa", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"train": {"name": "train", "num_bytes": 1271393601, "num_examples": 87622, "dataset_name": "triviaqa"}, "validation": {"name": "validation", "num_bytes": 163819509, "num_examples": 11313, "dataset_name": "triviaqa"}}, "download_checksums": {"http://eaidata.bmk.sh/data/triviaqa-unfiltered.tar.gz": {"num_bytes": 546481381, "checksum": "adc19b42769062d241a8fbe834c56e58598d9322eb6c614e9f33a68a2cf5523e"}}, "download_size": 546481381, "post_processing_size": null, "dataset_size": 1435213110, "size_in_bytes": 1981694491}}
\ No newline at end of file

lm_eval/datasets/truthfulqa/dataset_infos.json

-{"multiple_choice": {"description": "TruthfulQA is a benchmark to measure whether a language model is truthful in\ngenerating answers to questions. The benchmark comprises 817 questions that\nspan 38 categories, including health, law, finance and politics. Questions are\ncrafted so that some humans would answer falsely due to a false belief or\nmisconception. To perform well, models must avoid generating false answers\nlearned from imitating human texts.\n\nThe multiple choice TruthfulQA task", "citation": "@misc{lin2021truthfulqa,\n    title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},\n    author={Stephanie Lin and Jacob Hilton and Owain Evans},\n    year={2021},\n    eprint={2109.07958},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/sylinrl/TruthfulQA", "license": "", "features": {"question": {"dtype": "string", "id": null, "_type": "Value"}, "mc1_targets": {"choices": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "labels": {"feature": {"dtype": "int32", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "mc2_targets": {"choices": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "labels": {"feature": {"dtype": "int32", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "truthfulqa", "config_name": "multiple_choice", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 610333, "num_examples": 817, "dataset_name": "truthfulqa"}}, "download_checksums": {"https://raw.githubusercontent.com/sylinrl/TruthfulQA/013686a06be7a7bde5bf8223943e106c7250123c/data/mc_task.json": {"num_bytes": 710607, "checksum": "6eb4125d25750c0145c4be2dce00440736684ab6f74ce6bff2139571cc758954"}}, "download_size": 710607, "post_processing_size": null, "dataset_size": 610333, "size_in_bytes": 1320940}, "generation": {"description": "TruthfulQA is a benchmark to measure whether a language model is truthful in\ngenerating answers to questions. The benchmark comprises 817 questions that\nspan 38 categories, including health, law, finance and politics. Questions are\ncrafted so that some humans would answer falsely due to a false belief or\nmisconception. To perform well, models must avoid generating false answers\nlearned from imitating human texts.\n\nThe generative TruthfulQA task", "citation": "@misc{lin2021truthfulqa,\n    title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},\n    author={Stephanie Lin and Jacob Hilton and Owain Evans},\n    year={2021},\n    eprint={2109.07958},\n    archivePrefix={arXiv},\n    primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/sylinrl/TruthfulQA", "license": "", "features": {"category": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "best_answer": {"dtype": "string", "id": null, "_type": "Value"}, "correct_answers": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "incorrect_answers": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "source": {"dtype": "string", "id": null, "_type": "Value"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "truthfulqa", "config_name": "generation", "version": {"version_str": "0.0.1", "description": null, "major": 0, "minor": 0, "patch": 1}, "splits": {"validation": {"name": "validation", "num_bytes": 463860, "num_examples": 817, "dataset_name": "truthfulqa"}}, "download_checksums": {"https://raw.githubusercontent.com/sylinrl/TruthfulQA/013686a06be7a7bde5bf8223943e106c7250123c/TruthfulQA.csv": {"num_bytes": 443723, "checksum": "8d7dd15f033196140f032d97d30f037da7a7b1192c3f36f9937c1850925335a2"}}, "download_size": 443723, "post_processing_size": null, "dataset_size": 463860, "size_in_bytes": 907583}}
\ No newline at end of file