five

open-llm-leaderboard/details_bigscience__bloom

收藏
Hugging Face2023-08-29 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_bigscience__bloom
下载链接
链接失效反馈
官方服务:
资源简介:
--- pretty_name: Evaluation run of None dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [None](https://huggingface.co/None) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 61 configuration, each one coresponding to one of the\ \ evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be\ \ found as a specific split in each configuration, the split being named using the\ \ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\ \nAn additional configuration \"results\" store all the aggregated results of the\ \ run (and is used to compute and display the agregated metrics on the [Open LLM\ \ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\ \nTo load the details from a run, you can for instance do the following:\n```python\n\ from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_bigscience__bloom\"\ ,\n\t\"harness_truthfulqa_mc_0\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\ \nThese are the [latest results from run 2023-08-29T12:19:54.390376](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloom/blob/main/results_2023-08-29T12%3A19%3A54.390376.json)(note\ \ that their might be results for other tasks in the repos if successive evals didn't\ \ cover the same tasks. You find each in the results and the \"latest\" split for\ \ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.315597821758106,\n\ \ \"acc_stderr\": 0.0334554445358342,\n \"acc_norm\": 0.31957868125391004,\n\ \ \"acc_norm_stderr\": 0.03344403068302842,\n \"mc1\": 0.2521419828641371,\n\ \ \"mc1_stderr\": 0.015201522246299962,\n \"mc2\": 0.3975962282334165,\n\ \ \"mc2_stderr\": 0.013579754303009808\n },\n \"harness|arc:challenge|25\"\ : {\n \"acc\": 0.4658703071672355,\n \"acc_stderr\": 0.014577311315231102,\n\ \ \"acc_norm\": 0.5042662116040956,\n \"acc_norm_stderr\": 0.014610858923956948\n\ \ },\n \"harness|hellaswag|10\": {\n \"acc\": 0.5676160127464649,\n\ \ \"acc_stderr\": 0.004943945069611452,\n \"acc_norm\": 0.7640908185620394,\n\ \ \"acc_norm_stderr\": 0.0042369801453443065\n },\n \"harness|hendrycksTest-abstract_algebra|5\"\ : {\n \"acc\": 0.24,\n \"acc_stderr\": 0.04292346959909283,\n \ \ \"acc_norm\": 0.24,\n \"acc_norm_stderr\": 0.04292346959909283\n \ \ },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.35555555555555557,\n\ \ \"acc_stderr\": 0.04135176749720386,\n \"acc_norm\": 0.35555555555555557,\n\ \ \"acc_norm_stderr\": 0.04135176749720386\n },\n \"harness|hendrycksTest-astronomy|5\"\ : {\n \"acc\": 0.25,\n \"acc_stderr\": 0.03523807393012047,\n \ \ \"acc_norm\": 0.25,\n \"acc_norm_stderr\": 0.03523807393012047\n \ \ },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.41,\n\ \ \"acc_stderr\": 0.049431107042371025,\n \"acc_norm\": 0.41,\n \ \ \"acc_norm_stderr\": 0.049431107042371025\n },\n \"harness|hendrycksTest-clinical_knowledge|5\"\ : {\n \"acc\": 0.3169811320754717,\n \"acc_stderr\": 0.028637235639800925,\n\ \ \"acc_norm\": 0.3169811320754717,\n \"acc_norm_stderr\": 0.028637235639800925\n\ \ },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.2847222222222222,\n\ \ \"acc_stderr\": 0.03773809990686934,\n \"acc_norm\": 0.2847222222222222,\n\ \ \"acc_norm_stderr\": 0.03773809990686934\n },\n \"harness|hendrycksTest-college_chemistry|5\"\ : {\n \"acc\": 0.18,\n \"acc_stderr\": 0.03861229196653694,\n \ \ \"acc_norm\": 0.18,\n \"acc_norm_stderr\": 0.03861229196653694\n \ \ },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\"\ : 0.31,\n \"acc_stderr\": 0.04648231987117316,\n \"acc_norm\": 0.31,\n\ \ \"acc_norm_stderr\": 0.04648231987117316\n },\n \"harness|hendrycksTest-college_mathematics|5\"\ : {\n \"acc\": 0.29,\n \"acc_stderr\": 0.04560480215720683,\n \ \ \"acc_norm\": 0.29,\n \"acc_norm_stderr\": 0.04560480215720683\n \ \ },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.24855491329479767,\n\ \ \"acc_stderr\": 0.03295304696818318,\n \"acc_norm\": 0.24855491329479767,\n\ \ \"acc_norm_stderr\": 0.03295304696818318\n },\n \"harness|hendrycksTest-college_physics|5\"\ : {\n \"acc\": 0.20588235294117646,\n \"acc_stderr\": 0.04023382273617749,\n\ \ \"acc_norm\": 0.20588235294117646,\n \"acc_norm_stderr\": 0.04023382273617749\n\ \ },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\":\ \ 0.34,\n \"acc_stderr\": 0.04760952285695235,\n \"acc_norm\": 0.34,\n\ \ \"acc_norm_stderr\": 0.04760952285695235\n },\n \"harness|hendrycksTest-conceptual_physics|5\"\ : {\n \"acc\": 0.3276595744680851,\n \"acc_stderr\": 0.030683020843231004,\n\ \ \"acc_norm\": 0.3276595744680851,\n \"acc_norm_stderr\": 0.030683020843231004\n\ \ },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.24561403508771928,\n\ \ \"acc_stderr\": 0.040493392977481425,\n \"acc_norm\": 0.24561403508771928,\n\ \ \"acc_norm_stderr\": 0.040493392977481425\n },\n \"harness|hendrycksTest-electrical_engineering|5\"\ : {\n \"acc\": 0.31724137931034485,\n \"acc_stderr\": 0.03878352372138623,\n\ \ \"acc_norm\": 0.31724137931034485,\n \"acc_norm_stderr\": 0.03878352372138623\n\ \ },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\"\ : 0.2804232804232804,\n \"acc_stderr\": 0.02313528797432563,\n \"\ acc_norm\": 0.2804232804232804,\n \"acc_norm_stderr\": 0.02313528797432563\n\ \ },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.24603174603174602,\n\ \ \"acc_stderr\": 0.03852273364924315,\n \"acc_norm\": 0.24603174603174602,\n\ \ \"acc_norm_stderr\": 0.03852273364924315\n },\n \"harness|hendrycksTest-global_facts|5\"\ : {\n \"acc\": 0.35,\n \"acc_stderr\": 0.047937248544110196,\n \ \ \"acc_norm\": 0.35,\n \"acc_norm_stderr\": 0.047937248544110196\n \ \ },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\"\ : 0.2967741935483871,\n \"acc_stderr\": 0.02598850079241188,\n \"\ acc_norm\": 0.2967741935483871,\n \"acc_norm_stderr\": 0.02598850079241188\n\ \ },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\"\ : 0.28078817733990147,\n \"acc_stderr\": 0.03161856335358609,\n \"\ acc_norm\": 0.28078817733990147,\n \"acc_norm_stderr\": 0.03161856335358609\n\ \ },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \ \ \"acc\": 0.29,\n \"acc_stderr\": 0.045604802157206845,\n \"acc_norm\"\ : 0.29,\n \"acc_norm_stderr\": 0.045604802157206845\n },\n \"harness|hendrycksTest-high_school_european_history|5\"\ : {\n \"acc\": 0.2787878787878788,\n \"acc_stderr\": 0.03501438706296781,\n\ \ \"acc_norm\": 0.2787878787878788,\n \"acc_norm_stderr\": 0.03501438706296781\n\ \ },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\"\ : 0.3787878787878788,\n \"acc_stderr\": 0.03456088731993747,\n \"\ acc_norm\": 0.3787878787878788,\n \"acc_norm_stderr\": 0.03456088731993747\n\ \ },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n\ \ \"acc\": 0.29533678756476683,\n \"acc_stderr\": 0.0329229663915514,\n\ \ \"acc_norm\": 0.29533678756476683,\n \"acc_norm_stderr\": 0.0329229663915514\n\ \ },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \ \ \"acc\": 0.2230769230769231,\n \"acc_stderr\": 0.021107730127243998,\n\ \ \"acc_norm\": 0.2230769230769231,\n \"acc_norm_stderr\": 0.021107730127243998\n\ \ },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"\ acc\": 0.2740740740740741,\n \"acc_stderr\": 0.027195934804085622,\n \ \ \"acc_norm\": 0.2740740740740741,\n \"acc_norm_stderr\": 0.027195934804085622\n\ \ },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \ \ \"acc\": 0.24789915966386555,\n \"acc_stderr\": 0.028047967224176896,\n\ \ \"acc_norm\": 0.24789915966386555,\n \"acc_norm_stderr\": 0.028047967224176896\n\ \ },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\"\ : 0.24503311258278146,\n \"acc_stderr\": 0.03511807571804726,\n \"\ acc_norm\": 0.24503311258278146,\n \"acc_norm_stderr\": 0.03511807571804726\n\ \ },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\"\ : 0.4,\n \"acc_stderr\": 0.021004201260420078,\n \"acc_norm\": 0.4,\n\ \ \"acc_norm_stderr\": 0.021004201260420078\n },\n \"harness|hendrycksTest-high_school_statistics|5\"\ : {\n \"acc\": 0.21296296296296297,\n \"acc_stderr\": 0.02792096314799366,\n\ \ \"acc_norm\": 0.21296296296296297,\n \"acc_norm_stderr\": 0.02792096314799366\n\ \ },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\"\ : 0.30392156862745096,\n \"acc_stderr\": 0.032282103870378914,\n \"\ acc_norm\": 0.30392156862745096,\n \"acc_norm_stderr\": 0.032282103870378914\n\ \ },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"\ acc\": 0.3206751054852321,\n \"acc_stderr\": 0.03038193194999041,\n \ \ \"acc_norm\": 0.3206751054852321,\n \"acc_norm_stderr\": 0.03038193194999041\n\ \ },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.3901345291479821,\n\ \ \"acc_stderr\": 0.03273766725459157,\n \"acc_norm\": 0.3901345291479821,\n\ \ \"acc_norm_stderr\": 0.03273766725459157\n },\n \"harness|hendrycksTest-human_sexuality|5\"\ : {\n \"acc\": 0.3282442748091603,\n \"acc_stderr\": 0.041184385658062976,\n\ \ \"acc_norm\": 0.3282442748091603,\n \"acc_norm_stderr\": 0.041184385658062976\n\ \ },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\":\ \ 0.371900826446281,\n \"acc_stderr\": 0.04412015806624502,\n \"acc_norm\"\ : 0.371900826446281,\n \"acc_norm_stderr\": 0.04412015806624502\n },\n\ \ \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.37962962962962965,\n\ \ \"acc_stderr\": 0.04691521224077742,\n \"acc_norm\": 0.37962962962962965,\n\ \ \"acc_norm_stderr\": 0.04691521224077742\n },\n \"harness|hendrycksTest-logical_fallacies|5\"\ : {\n \"acc\": 0.2822085889570552,\n \"acc_stderr\": 0.03536117886664743,\n\ \ \"acc_norm\": 0.2822085889570552,\n \"acc_norm_stderr\": 0.03536117886664743\n\ \ },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.26785714285714285,\n\ \ \"acc_stderr\": 0.04203277291467763,\n \"acc_norm\": 0.26785714285714285,\n\ \ \"acc_norm_stderr\": 0.04203277291467763\n },\n \"harness|hendrycksTest-management|5\"\ : {\n \"acc\": 0.2621359223300971,\n \"acc_stderr\": 0.043546310772605956,\n\ \ \"acc_norm\": 0.2621359223300971,\n \"acc_norm_stderr\": 0.043546310772605956\n\ \ },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.4230769230769231,\n\ \ \"acc_stderr\": 0.032366121762202014,\n \"acc_norm\": 0.4230769230769231,\n\ \ \"acc_norm_stderr\": 0.032366121762202014\n },\n \"harness|hendrycksTest-medical_genetics|5\"\ : {\n \"acc\": 0.4,\n \"acc_stderr\": 0.049236596391733084,\n \ \ \"acc_norm\": 0.4,\n \"acc_norm_stderr\": 0.049236596391733084\n \ \ },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.40102171136653897,\n\ \ \"acc_stderr\": 0.017526133150124572,\n \"acc_norm\": 0.40102171136653897,\n\ \ \"acc_norm_stderr\": 0.017526133150124572\n },\n \"harness|hendrycksTest-moral_disputes|5\"\ : {\n \"acc\": 0.3670520231213873,\n \"acc_stderr\": 0.025950054337654096,\n\ \ \"acc_norm\": 0.3670520231213873,\n \"acc_norm_stderr\": 0.025950054337654096\n\ \ },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.2424581005586592,\n\ \ \"acc_stderr\": 0.014333522059217889,\n \"acc_norm\": 0.2424581005586592,\n\ \ \"acc_norm_stderr\": 0.014333522059217889\n },\n \"harness|hendrycksTest-nutrition|5\"\ : {\n \"acc\": 0.28431372549019607,\n \"acc_stderr\": 0.025829163272757482,\n\ \ \"acc_norm\": 0.28431372549019607,\n \"acc_norm_stderr\": 0.025829163272757482\n\ \ },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.35691318327974275,\n\ \ \"acc_stderr\": 0.027210420375934023,\n \"acc_norm\": 0.35691318327974275,\n\ \ \"acc_norm_stderr\": 0.027210420375934023\n },\n \"harness|hendrycksTest-prehistory|5\"\ : {\n \"acc\": 0.32407407407407407,\n \"acc_stderr\": 0.026041766202717163,\n\ \ \"acc_norm\": 0.32407407407407407,\n \"acc_norm_stderr\": 0.026041766202717163\n\ \ },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"\ acc\": 0.2907801418439716,\n \"acc_stderr\": 0.027090664368353178,\n \ \ \"acc_norm\": 0.2907801418439716,\n \"acc_norm_stderr\": 0.027090664368353178\n\ \ },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.27835723598435463,\n\ \ \"acc_stderr\": 0.011446990197380982,\n \"acc_norm\": 0.27835723598435463,\n\ \ \"acc_norm_stderr\": 0.011446990197380982\n },\n \"harness|hendrycksTest-professional_medicine|5\"\ : {\n \"acc\": 0.24632352941176472,\n \"acc_stderr\": 0.02617343857052,\n\ \ \"acc_norm\": 0.24632352941176472,\n \"acc_norm_stderr\": 0.02617343857052\n\ \ },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"\ acc\": 0.32189542483660133,\n \"acc_stderr\": 0.018901015322093085,\n \ \ \"acc_norm\": 0.32189542483660133,\n \"acc_norm_stderr\": 0.018901015322093085\n\ \ },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.33636363636363636,\n\ \ \"acc_stderr\": 0.04525393596302505,\n \"acc_norm\": 0.33636363636363636,\n\ \ \"acc_norm_stderr\": 0.04525393596302505\n },\n \"harness|hendrycksTest-security_studies|5\"\ : {\n \"acc\": 0.31020408163265306,\n \"acc_stderr\": 0.02961345987248438,\n\ \ \"acc_norm\": 0.31020408163265306,\n \"acc_norm_stderr\": 0.02961345987248438\n\ \ },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.32338308457711445,\n\ \ \"acc_stderr\": 0.03307615947979033,\n \"acc_norm\": 0.32338308457711445,\n\ \ \"acc_norm_stderr\": 0.03307615947979033\n },\n \"harness|hendrycksTest-us_foreign_policy|5\"\ : {\n \"acc\": 0.4,\n \"acc_stderr\": 0.049236596391733084,\n \ \ \"acc_norm\": 0.4,\n \"acc_norm_stderr\": 0.049236596391733084\n \ \ },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.3072289156626506,\n\ \ \"acc_stderr\": 0.03591566797824663,\n \"acc_norm\": 0.3072289156626506,\n\ \ \"acc_norm_stderr\": 0.03591566797824663\n },\n \"harness|hendrycksTest-world_religions|5\"\ : {\n \"acc\": 0.4444444444444444,\n \"acc_stderr\": 0.0381107966983353,\n\ \ \"acc_norm\": 0.4444444444444444,\n \"acc_norm_stderr\": 0.0381107966983353\n\ \ },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.2521419828641371,\n\ \ \"mc1_stderr\": 0.015201522246299962,\n \"mc2\": 0.3975962282334165,\n\ \ \"mc2_stderr\": 0.013579754303009808\n }\n}\n```" repo_url: https://huggingface.co/None leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard point_of_contact: clementine@hf.co configs: - config_name: harness_arc_challenge_25 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|arc:challenge|25_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hellaswag|10_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-management|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-management|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-08-29T12:19:54.390376.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-international_law|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-management|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-marketing|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-sociology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-virology|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T12:19:54.390376.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_08_29T12_19_54.390376 path: - '**/details_harness|truthfulqa:mc|0_2023-08-29T12:19:54.390376.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-08-29T12:19:54.390376.parquet' - config_name: results data_files: - split: 2023_08_29T12_19_54.390376 path: - results_2023-08-29T12:19:54.390376.parquet - split: latest path: - results_2023-08-29T12:19:54.390376.parquet --- # Dataset Card for Evaluation run of None ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/None - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** clementine@hf.co ### Dataset Summary Dataset automatically created during the evaluation run of model [None](https://huggingface.co/None) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 61 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the agregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)). To load the details from a run, you can for instance do the following: ```python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bigscience__bloom", "harness_truthfulqa_mc_0", split="train") ``` ## Latest results These are the [latest results from run 2023-08-29T12:19:54.390376](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloom/blob/main/results_2023-08-29T12%3A19%3A54.390376.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval): ```python { "all": { "acc": 0.315597821758106, "acc_stderr": 0.0334554445358342, "acc_norm": 0.31957868125391004, "acc_norm_stderr": 0.03344403068302842, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299962, "mc2": 0.3975962282334165, "mc2_stderr": 0.013579754303009808 }, "harness|arc:challenge|25": { "acc": 0.4658703071672355, "acc_stderr": 0.014577311315231102, "acc_norm": 0.5042662116040956, "acc_norm_stderr": 0.014610858923956948 }, "harness|hellaswag|10": { "acc": 0.5676160127464649, "acc_stderr": 0.004943945069611452, "acc_norm": 0.7640908185620394, "acc_norm_stderr": 0.0042369801453443065 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720386, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3169811320754717, "acc_stderr": 0.028637235639800925, "acc_norm": 0.3169811320754717, "acc_norm_stderr": 0.028637235639800925 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686934, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686934 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24855491329479767, "acc_stderr": 0.03295304696818318, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617749, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617749 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3276595744680851, "acc_stderr": 0.030683020843231004, "acc_norm": 0.3276595744680851, "acc_norm_stderr": 0.030683020843231004 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481425, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481425 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.31724137931034485, "acc_stderr": 0.03878352372138623, "acc_norm": 0.31724137931034485, "acc_norm_stderr": 0.03878352372138623 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2804232804232804, "acc_stderr": 0.02313528797432563, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.02313528797432563 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.24603174603174602, "acc_stderr": 0.03852273364924315, "acc_norm": 0.24603174603174602, "acc_norm_stderr": 0.03852273364924315 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2967741935483871, "acc_stderr": 0.02598850079241188, "acc_norm": 0.2967741935483871, "acc_norm_stderr": 0.02598850079241188 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.03161856335358609, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.03161856335358609 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3787878787878788, "acc_stderr": 0.03456088731993747, "acc_norm": 0.3787878787878788, "acc_norm_stderr": 0.03456088731993747 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.29533678756476683, "acc_stderr": 0.0329229663915514, "acc_norm": 0.29533678756476683, "acc_norm_stderr": 0.0329229663915514 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2230769230769231, "acc_stderr": 0.021107730127243998, "acc_norm": 0.2230769230769231, "acc_norm_stderr": 0.021107730127243998 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2740740740740741, "acc_stderr": 0.027195934804085622, "acc_norm": 0.2740740740740741, "acc_norm_stderr": 0.027195934804085622 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.24789915966386555, "acc_stderr": 0.028047967224176896, "acc_norm": 0.24789915966386555, "acc_norm_stderr": 0.028047967224176896 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.24503311258278146, "acc_stderr": 0.03511807571804726, "acc_norm": 0.24503311258278146, "acc_norm_stderr": 0.03511807571804726 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.4, "acc_stderr": 0.021004201260420078, "acc_norm": 0.4, "acc_norm_stderr": 0.021004201260420078 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.21296296296296297, "acc_stderr": 0.02792096314799366, "acc_norm": 0.21296296296296297, "acc_norm_stderr": 0.02792096314799366 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.30392156862745096, "acc_stderr": 0.032282103870378914, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.032282103870378914 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.3206751054852321, "acc_stderr": 0.03038193194999041, "acc_norm": 0.3206751054852321, "acc_norm_stderr": 0.03038193194999041 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.3901345291479821, "acc_stderr": 0.03273766725459157, "acc_norm": 0.3901345291479821, "acc_norm_stderr": 0.03273766725459157 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.3282442748091603, "acc_stderr": 0.041184385658062976, "acc_norm": 0.3282442748091603, "acc_norm_stderr": 0.041184385658062976 }, "harness|hendrycksTest-international_law|5": { "acc": 0.371900826446281, "acc_stderr": 0.04412015806624502, "acc_norm": 0.371900826446281, "acc_norm_stderr": 0.04412015806624502 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.37962962962962965, "acc_stderr": 0.04691521224077742, "acc_norm": 0.37962962962962965, "acc_norm_stderr": 0.04691521224077742 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.2822085889570552, "acc_stderr": 0.03536117886664743, "acc_norm": 0.2822085889570552, "acc_norm_stderr": 0.03536117886664743 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.26785714285714285, "acc_stderr": 0.04203277291467763, "acc_norm": 0.26785714285714285, "acc_norm_stderr": 0.04203277291467763 }, "harness|hendrycksTest-management|5": { "acc": 0.2621359223300971, "acc_stderr": 0.043546310772605956, "acc_norm": 0.2621359223300971, "acc_norm_stderr": 0.043546310772605956 }, "harness|hendrycksTest-marketing|5": { "acc": 0.4230769230769231, "acc_stderr": 0.032366121762202014, "acc_norm": 0.4230769230769231, "acc_norm_stderr": 0.032366121762202014 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.40102171136653897, "acc_stderr": 0.017526133150124572, "acc_norm": 0.40102171136653897, "acc_norm_stderr": 0.017526133150124572 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.3670520231213873, "acc_stderr": 0.025950054337654096, "acc_norm": 0.3670520231213873, "acc_norm_stderr": 0.025950054337654096 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2424581005586592, "acc_stderr": 0.014333522059217889, "acc_norm": 0.2424581005586592, "acc_norm_stderr": 0.014333522059217889 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.28431372549019607, "acc_stderr": 0.025829163272757482, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.025829163272757482 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.35691318327974275, "acc_stderr": 0.027210420375934023, "acc_norm": 0.35691318327974275, "acc_norm_stderr": 0.027210420375934023 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.32407407407407407, "acc_stderr": 0.026041766202717163, "acc_norm": 0.32407407407407407, "acc_norm_stderr": 0.026041766202717163 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.2907801418439716, "acc_stderr": 0.027090664368353178, "acc_norm": 0.2907801418439716, "acc_norm_stderr": 0.027090664368353178 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.27835723598435463, "acc_stderr": 0.011446990197380982, "acc_norm": 0.27835723598435463, "acc_norm_stderr": 0.011446990197380982 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.24632352941176472, "acc_stderr": 0.02617343857052, "acc_norm": 0.24632352941176472, "acc_norm_stderr": 0.02617343857052 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.32189542483660133, "acc_stderr": 0.018901015322093085, "acc_norm": 0.32189542483660133, "acc_norm_stderr": 0.018901015322093085 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.33636363636363636, "acc_stderr": 0.04525393596302505, "acc_norm": 0.33636363636363636, "acc_norm_stderr": 0.04525393596302505 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.31020408163265306, "acc_stderr": 0.02961345987248438, "acc_norm": 0.31020408163265306, "acc_norm_stderr": 0.02961345987248438 }, "harness|hendrycksTest-sociology|5": { "acc": 0.32338308457711445, "acc_stderr": 0.03307615947979033, "acc_norm": 0.32338308457711445, "acc_norm_stderr": 0.03307615947979033 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-virology|5": { "acc": 0.3072289156626506, "acc_stderr": 0.03591566797824663, "acc_norm": 0.3072289156626506, "acc_norm_stderr": 0.03591566797824663 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.4444444444444444, "acc_stderr": 0.0381107966983353, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.0381107966983353 }, "harness|truthfulqa:mc|0": { "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299962, "mc2": 0.3975962282334165, "mc2_stderr": 0.013579754303009808 } } ``` ### Supported Tasks and Leaderboards [More Information Needed] ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在模型NoneOpen LLM Leaderboard上的评估运行期间自动创建的。数据集包含61个配置,每个配置对应一个评估任务。数据集从1次运行中创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新的结果。

数据集结构

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2023_08_29T12_19_54.390376
      • 路径: **/details_harness|arc:challenge|25_2023-08-29T12:19:54.390376.parquet
    • split: latest
      • 路径: **/details_harness|arc:challenge|25_2023-08-29T12:19:54.390376.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_08_29T12_19_54.390376
      • 路径: **/details_harness|hellaswag|10_2023-08-29T12:19:54.390376.parquet
    • split: latest
      • 路径: **/details_harness|hellaswag|10_2023-08-29T12:19:54.390376.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_08_29T12_19_54.390376
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-public_relations|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-security_studies|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-sociology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-virology|5_2023-08-29T12:19:54.390376.parquet
        • **/details_harness|hendrycksTest-world_religions|5_2023-08-29T12:19:54.390376.parquet

最新结果

以下是2023年8月29日12:19:54.390376运行的最新结果:

python { "all": { "acc": 0.315597821758106, "acc_stderr": 0.0334554445358342, "acc_norm": 0.31957868125391004, "acc_norm_stderr": 0.03344403068302842, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299962, "mc2": 0.3975962282334165, "mc2_stderr": 0.013579754303009808 }, "harness|arc:challenge|25": { "acc": 0.4658703071672355, "acc_stderr": 0.014577311315231102, "acc_norm": 0.5042662116040956, "acc_norm_stderr": 0.014610858923956948 }, "harness|hellaswag|10": { "acc": 0.5676160127464649, "acc_stderr": 0.004943945069611452, "acc_norm": 0.7640908185620394, "acc_norm_stderr": 0.0042369801453443065 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.0429234

搜集汇总
数据集介绍
main_image_url
构建方式
在大型语言模型评估领域,Open LLM Leaderboard 为模型性能的横向对比提供了标准化平台。该数据集正是针对 BigScience BLOOM 模型在排行榜上的评估过程而自动构建的。其构建方式独特,由一次完整的评估运行产生,并将该次运行的详细结果按照评估任务拆分为61个独立的配置项。每个配置项对应一个具体的评估基准,如 ARC Challenge 或 HellaSwag。评估运行的每次执行都会被记录为一个独立的数据集分割,分割名称采用运行的时间戳进行标识,从而保证了版本的可追溯性。此外,数据集内设有一个名为“results”的专用配置,用于汇总并存储该次运行的所有聚合指标,为排行榜上最终分数的计算与展示提供数据基础。
特点
该数据集最显著的特点在于其结构化的组织方式与历史追溯能力。它并非单一表格,而是由61个配置构成的复合数据集,每个配置专注于一个评估任务,使得研究者可以精准定位特定维度的模型表现。每个评估运行都会产生一个以时间戳命名的数据分割,这种设计不仅清晰记录了每次评估的独立结果,更通过“train”分割始终指向最新运行结果的方式,实现了对模型性能动态变化的持续追踪。这种架构赋予了数据集高度的可扩展性与版本控制能力,便于进行跨时间维度的性能对比与分析。
使用方法
使用该数据集时,研究者可通过 Hugging Face 的 datasets 库进行灵活加载。若要获取某次特定评估运行的详细结果,只需指定任务对应的配置名称及运行的时间戳分割即可。例如,加载 truthfulqa_mc 任务的评估细节,可通过 load_dataset 函数并传入配置名“harness_truthfulqa_mc_0”与分割“train”来实现。对于需要分析聚合性能的场景,直接访问“results”配置即可获取到所有任务的综合指标。这种模块化的访问方式,允许用户根据研究需求,快速提取单一任务的细粒度数据或全量评估的宏观概览,极大便利了模型评估结果的重现与深入分析。
背景与挑战
背景概述
大语言模型(LLM)的迅猛发展催生了对其性能进行系统化、标准化评估的迫切需求。在此背景下,Hugging Face团队于2023年发起了Open LLM Leaderboard项目,旨在构建一个开放、透明且可复现的模型评测平台。该数据集作为bigscience/bloom模型在Leaderboard上的评测记录,由Clementine Fourrier等人主导创建,核心研究问题在于如何通过多维度、多任务的评测体系,全面衡量LLM在推理、知识理解与安全性等方面的能力。该数据集收录了61个评测任务的详细结果,涵盖ARC挑战赛、HellaSwag常识推理、MMLU多学科知识以及TruthfulQA真实性评估等,为社区提供了宝贵的基准数据。其影响力体现在推动了LLM评测标准的统一化,促进了模型之间的公平比较与迭代优化。
当前挑战
该数据集所面临的挑战具有双重性。就领域问题而言,LLM评测的核心难题在于如何设计能够真实反映模型泛化能力与潜在风险的评估任务,例如现有基准常受限于数据污染与任务饱和,难以捕捉模型在开放域场景下的鲁棒性与事实一致性。就构建过程而言,挑战体现在三个方面:其一,评测任务覆盖学科广泛(如医学、法律、物理等),需确保数据标注的准确性与领域专家的参与;其二,模型输出的多样性要求构建细粒度的评估指标(如MC1/MC2),并处理不同任务间指标兼容性问题;其三,评测流程的自动化与版本控制面临挑战,需确保每次运行结果的可追溯性与可复现性,如该数据集通过时间戳分割管理多次运行结果,但并行评测与结果聚合的稳定性仍是技术难点。
常用场景
经典使用场景
在自然语言处理领域,open-llm-leaderboard/details_bigscience__bloom数据集是评估大型语言模型(LLM)性能的标准化基准。该数据集整合了61个任务配置,涵盖常识推理(如ARC-Challenge)、文本生成(如HellaSwag)、多学科知识问答(如MMLU)及事实一致性(如TruthfulQA)等核心评估维度。研究者通常利用该数据集对模型进行零样本或少样本测试,通过计算准确率(acc)、归一化准确率(acc_norm)及多选指标(mc1/mc2)等关键分数,系统性地对比不同规模、架构或训练策略的LLM在多样化场景下的泛化能力,从而评判模型的综合水平。
实际应用
实际应用中,该数据集为工业界部署LLM提供了关键的质量控制依据。企业可借助此基准筛选适用于智能客服、教育辅导或内容生成等场景的模型,例如通过TruthfulQA指标评估模型避免生成误导性信息的可靠性。此外,数据集的细粒度结果(如各学科准确率)能指导特定领域模型的微调方向,例如在医疗或法律应用中优先提升相关子任务的得分。该数据集还支持持续集成流程,允许开发团队追踪模型迭代过程中的性能变化,确保产品更新不引入退化。
衍生相关工作
该数据集衍生出多项推动LLM评估发展的经典工作。基于其标准化框架,研究者构建了Open LLM Leaderboard排行榜,形成社区驱动的模型竞技平台,激励了如BLOOM、LLaMA等系列模型的公开比较。此外,数据集中的MMLU子集被广泛用于开发少样本学习策略(如Chain-of-Thought提示)和评估多语言模型能力,而TruthfulQA任务则催生了关于模型事实性与幻觉抑制的专项研究。这些工作共同深化了对LLM能力边界与局限性的认知。
以上内容由遇见数据集搜集并总结生成
二维码
社区交流群
二维码
科研交流群
商业服务