fix for merge from master

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