open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-6.7b

--- pretty_name: Evaluation run of AI-Sweden-Models/gpt-sw3-6.7b dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [AI-Sweden-Models/gpt-sw3-6.7b](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b)\ \ on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 64 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 aggregated 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_AI-Sweden-Models__gpt-sw3-6.7b_public\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2023-11-19T14:20:27.241108](https://huggingface.co/datasets/open-llm-leaderboard/details_AI-Sweden-Models__gpt-sw3-6.7b_public/blob/main/results_2023-11-19T14-20-27.241108.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\": 0.26572380055428,\n\ \ \"acc_stderr\": 0.03108769443217598,\n \"acc_norm\": 0.26762761682482883,\n\ \ \"acc_norm_stderr\": 0.031880299374266195,\n \"mc1\": 0.23255813953488372,\n\ \ \"mc1_stderr\": 0.014789157531080508,\n \"mc2\": 0.39038444805230477,\n\ \ \"mc2_stderr\": 0.013873169667140115,\n \"em\": 0.04058305369127517,\n\ \ \"em_stderr\": 0.002020764506779191,\n \"f1\": 0.08923238255033483,\n\ \ \"f1_stderr\": 0.0023387637858432947\n },\n \"harness|arc:challenge|25\"\ : {\n \"acc\": 0.32081911262798635,\n \"acc_stderr\": 0.013640943091946526,\n\ \ \"acc_norm\": 0.363481228668942,\n \"acc_norm_stderr\": 0.014056207319068285\n\ \ },\n \"harness|hellaswag|10\": {\n \"acc\": 0.4570802628958375,\n\ \ \"acc_stderr\": 0.004971364031062592,\n \"acc_norm\": 0.6075482971519618,\n\ \ \"acc_norm_stderr\": 0.0048729844929680105\n },\n \"harness|hendrycksTest-abstract_algebra|5\"\ : {\n \"acc\": 0.26,\n \"acc_stderr\": 0.04408440022768081,\n \ \ \"acc_norm\": 0.26,\n \"acc_norm_stderr\": 0.04408440022768081\n \ \ },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.34074074074074073,\n\ \ \"acc_stderr\": 0.04094376269996793,\n \"acc_norm\": 0.34074074074074073,\n\ \ \"acc_norm_stderr\": 0.04094376269996793\n },\n \"harness|hendrycksTest-astronomy|5\"\ : {\n \"acc\": 0.3026315789473684,\n \"acc_stderr\": 0.037385206761196665,\n\ \ \"acc_norm\": 0.3026315789473684,\n \"acc_norm_stderr\": 0.037385206761196665\n\ \ },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.23,\n\ \ \"acc_stderr\": 0.04229525846816506,\n \"acc_norm\": 0.23,\n \ \ \"acc_norm_stderr\": 0.04229525846816506\n },\n \"harness|hendrycksTest-clinical_knowledge|5\"\ : {\n \"acc\": 0.2339622641509434,\n \"acc_stderr\": 0.02605529690115292,\n\ \ \"acc_norm\": 0.2339622641509434,\n \"acc_norm_stderr\": 0.02605529690115292\n\ \ },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.2638888888888889,\n\ \ \"acc_stderr\": 0.03685651095897532,\n \"acc_norm\": 0.2638888888888889,\n\ \ \"acc_norm_stderr\": 0.03685651095897532\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\"\ : 0.28,\n \"acc_stderr\": 0.04512608598542129,\n \"acc_norm\": 0.28,\n\ \ \"acc_norm_stderr\": 0.04512608598542129\n },\n \"harness|hendrycksTest-college_mathematics|5\"\ : {\n \"acc\": 0.3,\n \"acc_stderr\": 0.046056618647183814,\n \ \ \"acc_norm\": 0.3,\n \"acc_norm_stderr\": 0.046056618647183814\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\": 0.19607843137254902,\n \"acc_stderr\": 0.03950581861179963,\n\ \ \"acc_norm\": 0.19607843137254902,\n \"acc_norm_stderr\": 0.03950581861179963\n\ \ },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\":\ \ 0.26,\n \"acc_stderr\": 0.044084400227680794,\n \"acc_norm\": 0.26,\n\ \ \"acc_norm_stderr\": 0.044084400227680794\n },\n \"harness|hendrycksTest-conceptual_physics|5\"\ : {\n \"acc\": 0.2127659574468085,\n \"acc_stderr\": 0.026754391348039776,\n\ \ \"acc_norm\": 0.2127659574468085,\n \"acc_norm_stderr\": 0.026754391348039776\n\ \ },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.2631578947368421,\n\ \ \"acc_stderr\": 0.041424397194893624,\n \"acc_norm\": 0.2631578947368421,\n\ \ \"acc_norm_stderr\": 0.041424397194893624\n },\n \"harness|hendrycksTest-electrical_engineering|5\"\ : {\n \"acc\": 0.27586206896551724,\n \"acc_stderr\": 0.037245636197746325,\n\ \ \"acc_norm\": 0.27586206896551724,\n \"acc_norm_stderr\": 0.037245636197746325\n\ \ },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\"\ : 0.2671957671957672,\n \"acc_stderr\": 0.02278967314577656,\n \"\ acc_norm\": 0.2671957671957672,\n \"acc_norm_stderr\": 0.02278967314577656\n\ \ },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.21428571428571427,\n\ \ \"acc_stderr\": 0.03670066451047181,\n \"acc_norm\": 0.21428571428571427,\n\ \ \"acc_norm_stderr\": 0.03670066451047181\n },\n \"harness|hendrycksTest-global_facts|5\"\ : {\n \"acc\": 0.38,\n \"acc_stderr\": 0.04878317312145633,\n \ \ \"acc_norm\": 0.38,\n \"acc_norm_stderr\": 0.04878317312145633\n \ \ },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.2645161290322581,\n\ \ \"acc_stderr\": 0.02509189237885928,\n \"acc_norm\": 0.2645161290322581,\n\ \ \"acc_norm_stderr\": 0.02509189237885928\n },\n \"harness|hendrycksTest-high_school_chemistry|5\"\ : {\n \"acc\": 0.26108374384236455,\n \"acc_stderr\": 0.03090379695211449,\n\ \ \"acc_norm\": 0.26108374384236455,\n \"acc_norm_stderr\": 0.03090379695211449\n\ \ },\n \"harness|hendrycksTest-high_school_computer_science|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-high_school_european_history|5\"\ : {\n \"acc\": 0.296969696969697,\n \"acc_stderr\": 0.035679697722680474,\n\ \ \"acc_norm\": 0.296969696969697,\n \"acc_norm_stderr\": 0.035679697722680474\n\ \ },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\"\ : 0.29797979797979796,\n \"acc_stderr\": 0.03258630383836556,\n \"\ acc_norm\": 0.29797979797979796,\n \"acc_norm_stderr\": 0.03258630383836556\n\ \ },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n\ \ \"acc\": 0.22797927461139897,\n \"acc_stderr\": 0.03027690994517826,\n\ \ \"acc_norm\": 0.22797927461139897,\n \"acc_norm_stderr\": 0.03027690994517826\n\ \ },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \ \ \"acc\": 0.2153846153846154,\n \"acc_stderr\": 0.020843034557462878,\n\ \ \"acc_norm\": 0.2153846153846154,\n \"acc_norm_stderr\": 0.020843034557462878\n\ \ },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"\ acc\": 0.25555555555555554,\n \"acc_stderr\": 0.02659393910184407,\n \ \ \"acc_norm\": 0.25555555555555554,\n \"acc_norm_stderr\": 0.02659393910184407\n\ \ },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \ \ \"acc\": 0.21008403361344538,\n \"acc_stderr\": 0.026461398717471874,\n\ \ \"acc_norm\": 0.21008403361344538,\n \"acc_norm_stderr\": 0.026461398717471874\n\ \ },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\"\ : 0.271523178807947,\n \"acc_stderr\": 0.03631329803969653,\n \"acc_norm\"\ : 0.271523178807947,\n \"acc_norm_stderr\": 0.03631329803969653\n },\n\ \ \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.24220183486238533,\n\ \ \"acc_stderr\": 0.018368176306598615,\n \"acc_norm\": 0.24220183486238533,\n\ \ \"acc_norm_stderr\": 0.018368176306598615\n },\n \"harness|hendrycksTest-high_school_statistics|5\"\ : {\n \"acc\": 0.2175925925925926,\n \"acc_stderr\": 0.0281396894448597,\n\ \ \"acc_norm\": 0.2175925925925926,\n \"acc_norm_stderr\": 0.0281396894448597\n\ \ },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\"\ : 0.27450980392156865,\n \"acc_stderr\": 0.03132179803083291,\n \"\ acc_norm\": 0.27450980392156865,\n \"acc_norm_stderr\": 0.03132179803083291\n\ \ },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"\ acc\": 0.2742616033755274,\n \"acc_stderr\": 0.029041333510598018,\n \ \ \"acc_norm\": 0.2742616033755274,\n \"acc_norm_stderr\": 0.029041333510598018\n\ \ },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.26905829596412556,\n\ \ \"acc_stderr\": 0.029763779406874975,\n \"acc_norm\": 0.26905829596412556,\n\ \ \"acc_norm_stderr\": 0.029763779406874975\n },\n \"harness|hendrycksTest-human_sexuality|5\"\ : {\n \"acc\": 0.25190839694656486,\n \"acc_stderr\": 0.03807387116306086,\n\ \ \"acc_norm\": 0.25190839694656486,\n \"acc_norm_stderr\": 0.03807387116306086\n\ \ },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\":\ \ 0.371900826446281,\n \"acc_stderr\": 0.04412015806624504,\n \"acc_norm\"\ : 0.371900826446281,\n \"acc_norm_stderr\": 0.04412015806624504\n },\n\ \ \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.24074074074074073,\n\ \ \"acc_stderr\": 0.041331194402438376,\n \"acc_norm\": 0.24074074074074073,\n\ \ \"acc_norm_stderr\": 0.041331194402438376\n },\n \"harness|hendrycksTest-logical_fallacies|5\"\ : {\n \"acc\": 0.3006134969325153,\n \"acc_stderr\": 0.03602511318806771,\n\ \ \"acc_norm\": 0.3006134969325153,\n \"acc_norm_stderr\": 0.03602511318806771\n\ \ },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.25,\n\ \ \"acc_stderr\": 0.04109974682633932,\n \"acc_norm\": 0.25,\n \ \ \"acc_norm_stderr\": 0.04109974682633932\n },\n \"harness|hendrycksTest-management|5\"\ : {\n \"acc\": 0.1941747572815534,\n \"acc_stderr\": 0.03916667762822583,\n\ \ \"acc_norm\": 0.1941747572815534,\n \"acc_norm_stderr\": 0.03916667762822583\n\ \ },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.25213675213675213,\n\ \ \"acc_stderr\": 0.02844796547623102,\n \"acc_norm\": 0.25213675213675213,\n\ \ \"acc_norm_stderr\": 0.02844796547623102\n },\n \"harness|hendrycksTest-medical_genetics|5\"\ : {\n \"acc\": 0.16,\n \"acc_stderr\": 0.0368452949177471,\n \ \ \"acc_norm\": 0.16,\n \"acc_norm_stderr\": 0.0368452949177471\n },\n\ \ \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.2796934865900383,\n\ \ \"acc_stderr\": 0.016050792148036543,\n \"acc_norm\": 0.2796934865900383,\n\ \ \"acc_norm_stderr\": 0.016050792148036543\n },\n \"harness|hendrycksTest-moral_disputes|5\"\ : {\n \"acc\": 0.2861271676300578,\n \"acc_stderr\": 0.02433214677913413,\n\ \ \"acc_norm\": 0.2861271676300578,\n \"acc_norm_stderr\": 0.02433214677913413\n\ \ },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.24692737430167597,\n\ \ \"acc_stderr\": 0.014422292204808835,\n \"acc_norm\": 0.24692737430167597,\n\ \ \"acc_norm_stderr\": 0.014422292204808835\n },\n \"harness|hendrycksTest-nutrition|5\"\ : {\n \"acc\": 0.25163398692810457,\n \"acc_stderr\": 0.024848018263875195,\n\ \ \"acc_norm\": 0.25163398692810457,\n \"acc_norm_stderr\": 0.024848018263875195\n\ \ },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.3054662379421222,\n\ \ \"acc_stderr\": 0.02616058445014049,\n \"acc_norm\": 0.3054662379421222,\n\ \ \"acc_norm_stderr\": 0.02616058445014049\n },\n \"harness|hendrycksTest-prehistory|5\"\ : {\n \"acc\": 0.2808641975308642,\n \"acc_stderr\": 0.025006469755799208,\n\ \ \"acc_norm\": 0.2808641975308642,\n \"acc_norm_stderr\": 0.025006469755799208\n\ \ },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"\ acc\": 0.26595744680851063,\n \"acc_stderr\": 0.02635806569888059,\n \ \ \"acc_norm\": 0.26595744680851063,\n \"acc_norm_stderr\": 0.02635806569888059\n\ \ },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.27444589308996087,\n\ \ \"acc_stderr\": 0.011397043163078154,\n \"acc_norm\": 0.27444589308996087,\n\ \ \"acc_norm_stderr\": 0.011397043163078154\n },\n \"harness|hendrycksTest-professional_medicine|5\"\ : {\n \"acc\": 0.16176470588235295,\n \"acc_stderr\": 0.02236867256288675,\n\ \ \"acc_norm\": 0.16176470588235295,\n \"acc_norm_stderr\": 0.02236867256288675\n\ \ },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"\ acc\": 0.27941176470588236,\n \"acc_stderr\": 0.018152871051538816,\n \ \ \"acc_norm\": 0.27941176470588236,\n \"acc_norm_stderr\": 0.018152871051538816\n\ \ },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.20909090909090908,\n\ \ \"acc_stderr\": 0.038950910157241364,\n \"acc_norm\": 0.20909090909090908,\n\ \ \"acc_norm_stderr\": 0.038950910157241364\n },\n \"harness|hendrycksTest-security_studies|5\"\ : {\n \"acc\": 0.2612244897959184,\n \"acc_stderr\": 0.02812342933514278,\n\ \ \"acc_norm\": 0.2612244897959184,\n \"acc_norm_stderr\": 0.02812342933514278\n\ \ },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.2537313432835821,\n\ \ \"acc_stderr\": 0.03076944496729601,\n \"acc_norm\": 0.2537313432835821,\n\ \ \"acc_norm_stderr\": 0.03076944496729601\n },\n \"harness|hendrycksTest-us_foreign_policy|5\"\ : {\n \"acc\": 0.28,\n \"acc_stderr\": 0.045126085985421276,\n \ \ \"acc_norm\": 0.28,\n \"acc_norm_stderr\": 0.045126085985421276\n \ \ },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.24096385542168675,\n\ \ \"acc_stderr\": 0.033293941190735296,\n \"acc_norm\": 0.24096385542168675,\n\ \ \"acc_norm_stderr\": 0.033293941190735296\n },\n \"harness|hendrycksTest-world_religions|5\"\ : {\n \"acc\": 0.29239766081871343,\n \"acc_stderr\": 0.034886477134579215,\n\ \ \"acc_norm\": 0.29239766081871343,\n \"acc_norm_stderr\": 0.034886477134579215\n\ \ },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.23255813953488372,\n\ \ \"mc1_stderr\": 0.014789157531080508,\n \"mc2\": 0.39038444805230477,\n\ \ \"mc2_stderr\": 0.013873169667140115\n },\n \"harness|winogrande|5\"\ : {\n \"acc\": 0.6069455406471981,\n \"acc_stderr\": 0.013727276249108437\n\ \ },\n \"harness|drop|3\": {\n \"em\": 0.04058305369127517,\n \ \ \"em_stderr\": 0.002020764506779191,\n \"f1\": 0.08923238255033483,\n\ \ \"f1_stderr\": 0.0023387637858432947\n },\n \"harness|gsm8k|5\":\ \ {\n \"acc\": 0.00530705079605762,\n \"acc_stderr\": 0.002001305720948049\n\ \ }\n}\n```" repo_url: https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard point_of_contact: [e-mail] configs: - config_name: harness_arc_challenge_25 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|arc:challenge|25_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2023-11-19T14-20-27.241108.parquet' - config_name: harness_drop_3 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|drop|3_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|drop|3_2023-11-19T14-20-27.241108.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|gsm8k|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hellaswag|10_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-management|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-international_law|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-management|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-marketing|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-sociology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-virology|5_2023-11-19T14-20-27.241108.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-anatomy|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-astronomy|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_biology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-college_physics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-computer_security|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-econometrics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-global_facts|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-human_aging|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-international_law|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-management|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-marketing|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-nutrition|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-philosophy|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-prehistory|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-professional_law|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-public_relations|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-security_studies|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-sociology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-virology|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|hendrycksTest-world_religions|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2023-11-19T14-20-27.241108.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|truthfulqa:mc|0_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2023-11-19T14-20-27.241108.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_11_19T14_20_27.241108 path: - '**/details_harness|winogrande|5_2023-11-19T14-20-27.241108.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-11-19T14-20-27.241108.parquet' - config_name: results data_files: - split: 2023_11_19T14_20_27.241108 path: - results_2023-11-19T14-20-27.241108.parquet - split: latest path: - results_2023-11-19T14-20-27.241108.parquet --- # Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-6.7b ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** [e-mail] ### Dataset Summary Dataset automatically created during the evaluation run of model [AI-Sweden-Models/gpt-sw3-6.7b](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 64 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 aggregated 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_AI-Sweden-Models__gpt-sw3-6.7b_public", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2023-11-19T14:20:27.241108](https://huggingface.co/datasets/open-llm-leaderboard/details_AI-Sweden-Models__gpt-sw3-6.7b_public/blob/main/results_2023-11-19T14-20-27.241108.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": 0.26572380055428, "acc_stderr": 0.03108769443217598, "acc_norm": 0.26762761682482883, "acc_norm_stderr": 0.031880299374266195, "mc1": 0.23255813953488372, "mc1_stderr": 0.014789157531080508, "mc2": 0.39038444805230477, "mc2_stderr": 0.013873169667140115, "em": 0.04058305369127517, "em_stderr": 0.002020764506779191, "f1": 0.08923238255033483, "f1_stderr": 0.0023387637858432947 }, "harness|arc:challenge|25": { "acc": 0.32081911262798635, "acc_stderr": 0.013640943091946526, "acc_norm": 0.363481228668942, "acc_norm_stderr": 0.014056207319068285 }, "harness|hellaswag|10": { "acc": 0.4570802628958375, "acc_stderr": 0.004971364031062592, "acc_norm": 0.6075482971519618, "acc_norm_stderr": 0.0048729844929680105 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.34074074074074073, "acc_stderr": 0.04094376269996793, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.04094376269996793 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3026315789473684, "acc_stderr": 0.037385206761196665, "acc_norm": 0.3026315789473684, "acc_norm_stderr": 0.037385206761196665 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "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": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2127659574468085, "acc_stderr": 0.026754391348039776, "acc_norm": 0.2127659574468085, "acc_norm_stderr": 0.026754391348039776 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577656 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.21428571428571427, "acc_stderr": 0.03670066451047181, "acc_norm": 0.21428571428571427, "acc_norm_stderr": 0.03670066451047181 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2645161290322581, "acc_stderr": 0.02509189237885928, "acc_norm": 0.2645161290322581, "acc_norm_stderr": 0.02509189237885928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.03090379695211449, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.03090379695211449 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.296969696969697, "acc_stderr": 0.035679697722680474, "acc_norm": 0.296969696969697, "acc_norm_stderr": 0.035679697722680474 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.29797979797979796, "acc_stderr": 0.03258630383836556, "acc_norm": 0.29797979797979796, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.03027690994517826, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.03027690994517826 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25555555555555554, "acc_stderr": 0.02659393910184407, "acc_norm": 0.25555555555555554, "acc_norm_stderr": 0.02659393910184407 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.21008403361344538, "acc_stderr": 0.026461398717471874, "acc_norm": 0.21008403361344538, "acc_norm_stderr": 0.026461398717471874 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.271523178807947, "acc_stderr": 0.03631329803969653, "acc_norm": 0.271523178807947, "acc_norm_stderr": 0.03631329803969653 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.24220183486238533, "acc_stderr": 0.018368176306598615, "acc_norm": 0.24220183486238533, "acc_norm_stderr": 0.018368176306598615 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.2175925925925926, "acc_stderr": 0.0281396894448597, "acc_norm": 0.2175925925925926, "acc_norm_stderr": 0.0281396894448597 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.27450980392156865, "acc_stderr": 0.03132179803083291, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.03132179803083291 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.2742616033755274, "acc_stderr": 0.029041333510598018, "acc_norm": 0.2742616033755274, "acc_norm_stderr": 0.029041333510598018 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.26905829596412556, "acc_stderr": 0.029763779406874975, "acc_norm": 0.26905829596412556, "acc_norm_stderr": 0.029763779406874975 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.25190839694656486, "acc_stderr": 0.03807387116306086, "acc_norm": 0.25190839694656486, "acc_norm_stderr": 0.03807387116306086 }, "harness|hendrycksTest-international_law|5": { "acc": 0.371900826446281, "acc_stderr": 0.04412015806624504, "acc_norm": 0.371900826446281, "acc_norm_stderr": 0.04412015806624504 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.24074074074074073, "acc_stderr": 0.041331194402438376, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.041331194402438376 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.3006134969325153, "acc_stderr": 0.03602511318806771, "acc_norm": 0.3006134969325153, "acc_norm_stderr": 0.03602511318806771 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.25, "acc_stderr": 0.04109974682633932, "acc_norm": 0.25, "acc_norm_stderr": 0.04109974682633932 }, "harness|hendrycksTest-management|5": { "acc": 0.1941747572815534, "acc_stderr": 0.03916667762822583, "acc_norm": 0.1941747572815534, "acc_norm_stderr": 0.03916667762822583 }, "harness|hendrycksTest-marketing|5": { "acc": 0.25213675213675213, "acc_stderr": 0.02844796547623102, "acc_norm": 0.25213675213675213, "acc_norm_stderr": 0.02844796547623102 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.16, "acc_stderr": 0.0368452949177471, "acc_norm": 0.16, "acc_norm_stderr": 0.0368452949177471 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.2796934865900383, "acc_stderr": 0.016050792148036543, "acc_norm": 0.2796934865900383, "acc_norm_stderr": 0.016050792148036543 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.2861271676300578, "acc_stderr": 0.02433214677913413, "acc_norm": 0.2861271676300578, "acc_norm_stderr": 0.02433214677913413 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.24692737430167597, "acc_stderr": 0.014422292204808835, "acc_norm": 0.24692737430167597, "acc_norm_stderr": 0.014422292204808835 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.25163398692810457, "acc_stderr": 0.024848018263875195, "acc_norm": 0.25163398692810457, "acc_norm_stderr": 0.024848018263875195 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.3054662379421222, "acc_stderr": 0.02616058445014049, "acc_norm": 0.3054662379421222, "acc_norm_stderr": 0.02616058445014049 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.2808641975308642, "acc_stderr": 0.025006469755799208, "acc_norm": 0.2808641975308642, "acc_norm_stderr": 0.025006469755799208 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.26595744680851063, "acc_stderr": 0.02635806569888059, "acc_norm": 0.26595744680851063, "acc_norm_stderr": 0.02635806569888059 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.27444589308996087, "acc_stderr": 0.011397043163078154, "acc_norm": 0.27444589308996087, "acc_norm_stderr": 0.011397043163078154 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.16176470588235295, "acc_stderr": 0.02236867256288675, "acc_norm": 0.16176470588235295, "acc_norm_stderr": 0.02236867256288675 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.27941176470588236, "acc_stderr": 0.018152871051538816, "acc_norm": 0.27941176470588236, "acc_norm_stderr": 0.018152871051538816 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.20909090909090908, "acc_stderr": 0.038950910157241364, "acc_norm": 0.20909090909090908, "acc_norm_stderr": 0.038950910157241364 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.2612244897959184, "acc_stderr": 0.02812342933514278, "acc_norm": 0.2612244897959184, "acc_norm_stderr": 0.02812342933514278 }, "harness|hendrycksTest-sociology|5": { "acc": 0.2537313432835821, "acc_stderr": 0.03076944496729601, "acc_norm": 0.2537313432835821, "acc_norm_stderr": 0.03076944496729601 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-virology|5": { "acc": 0.24096385542168675, "acc_stderr": 0.033293941190735296, "acc_norm": 0.24096385542168675, "acc_norm_stderr": 0.033293941190735296 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.29239766081871343, "acc_stderr": 0.034886477134579215, "acc_norm": 0.29239766081871343, "acc_norm_stderr": 0.034886477134579215 }, "harness|truthfulqa:mc|0": { "mc1": 0.23255813953488372, "mc1_stderr": 0.014789157531080508, "mc2": 0.39038444805230477, "mc2_stderr": 0.013873169667140115 }, "harness|winogrande|5": { "acc": 0.6069455406471981, "acc_stderr": 0.013727276249108437 }, "harness|drop|3": { "em": 0.04058305369127517, "em_stderr": 0.002020764506779191, "f1": 0.08923238255033483, "f1_stderr": 0.0023387637858432947 }, "harness|gsm8k|5": { "acc": 0.00530705079605762, "acc_stderr": 0.002001305720948049 } } ``` ### 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]

原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 AI-Sweden-Models/gpt-sw3-6.7b 进行评估时自动创建的，用于 Open LLM Leaderboard。

数据集结构

• 数据集包含 64 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，每个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。
• 额外的配置 "results" 存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_AI-Sweden-Models__gpt-sw3-6.7b_public", "harness_winogrande_5", split="train")

最新结果

以下是 2023-11-19T14:20:27.241108 运行 的最新结果：

python { "all": { "acc": 0.26572380055428, "acc_stderr": 0.03108769443217598, "acc_norm": 0.26762761682482883, "acc_norm_stderr": 0.031880299374266195, "mc1": 0.23255813953488372, "mc1_stderr": 0.014789157531080508, "mc2": 0.39038444805230477, "mc2_stderr": 0.013873169667140115, "em": 0.04058305369127517, "em_stderr": 0.002020764506779191, "f1": 0.08923238255033483, "f1_stderr": 0.0023387637858432947 }, "harness|arc:challenge|25": { "acc": 0.32081911262798635, "acc_stderr": 0.013640943091946526, "acc_norm": 0.363481228668942, "acc_norm_stderr": 0.014056207319068285 }, "harness|hellaswag|10": { "acc": 0.4570802628958375, "acc_stderr": 0.004971364031062592, "acc_norm": 0.6075482971519618, "acc_norm_stderr": 0.0048729844929680105 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.34074074074074073, "acc_stderr": 0.04094376269996793, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.04094376269996793 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3026315789473684, "acc_stderr": 0.037385206761196665, "acc_norm": 0.3026315789473684, "acc_norm_stderr": 0.037385206761196665 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "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": 0.28, "acc_stderr": 0.04512608598542129, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "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": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2127659574468085, "acc_stderr": 0.026754391348039776, "acc_norm": 0.2127659574468085, "acc_norm_stderr": 0.026754391348039776 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2671957671957672, "acc_stderr": 0.02278967314577656, "acc_norm": 0.2671957671957672, "acc_norm_stderr": 0.02278967314577656 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.21428571428571427, "acc_stderr": 0.03670066451047181, "acc_norm": 0.21428571428571427, "acc_norm_stderr": 0.03670066451047181 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145633, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2645161290322581, "acc_stderr": 0.02509189237885928, "acc_norm": 0.2645161290322581, "acc_norm_stderr": 0.02509189237885928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.03090379695211449, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.03090379695211449 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.296969696969697, "acc_stderr": 0.035679697722680474, "acc_norm": 0.296969696969697, "acc_norm_stderr": 0.035679697722680474 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.29797979797979796, "acc_stderr": 0.03258630383836556, "acc_norm": 0.29797979797979796, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.03027690994517826, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.03027690994517826 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154,

搜集汇总

数据集介绍

构建方式

在大型语言模型评估领域，Open LLM Leaderboard 为模型性能的标准化衡量提供了重要平台。该数据集是在对 AI-Sweden-Models/gpt-sw3-6.7b 模型进行评测的过程中自动生成的，其构建方式依托于一次完整的评估运行。数据集由 64 个配置组成，每个配置对应一个具体的评测任务，这些配置通过任务名称进行区分。每次运行的结果被存储为独立的 split，split 的命名采用运行的时间戳，而 'train' split 则始终指向最新一次运行的结果。此外，数据集还包含一个名为 'results' 的额外配置，用于汇总所有运行的聚合指标，并服务于 Leaderboard 上综合分数的计算与展示。

特点

该数据集的核心特点在于其结构化与时效性的有机结合。它通过细粒度的任务配置实现了评测结果的模块化组织，每个配置独立存储对应任务的详细指标，如准确率、标准差等，便于研究者针对特定任务进行深入分析。数据集的 split 机制以时间戳为标识，保留了历史运行轨迹，同时 'latest' split 自动指向最新结果，确保了数据的实时性。这种设计不仅支持对模型性能的纵向追踪，还通过 'results' 配置提供了宏观的聚合视角，使得整体评估与细节探究得以兼顾，充分满足了模型评测中对精度与可追溯性的双重需求。

使用方法

在应用层面，研究者可通过 Hugging Face 的 datasets 库便捷地加载该数据集。具体而言，使用 load_dataset 函数并指定数据集名称、目标配置（如 'harness_winogrande_5'）以及所需 split（如 'train'），即可获取对应任务的详细评测数据。这一接口设计使得用户能够灵活地选取特定任务或时间点的结果进行复现与分析。同时，数据集中存储的 JSON 格式聚合结果可直接用于 Leaderboard 的指标展示，或作为模型性能对比的基准。通过简单的 Python 调用，研究者即可将评测数据无缝集成至自己的分析流程中，从而高效地开展模型能力的评估与比较工作。

背景与挑战

背景概述

随着大语言模型（LLM）的蓬勃发展，如何系统性地评估其性能已成为自然语言处理领域的核心议题。在此背景下，Hugging Face团队于2023年推出了Open LLM Leaderboard，旨在为各类开源模型提供标准化、可复现的评测基准。该数据集记录了AI-Sweden-Models团队开发的gpt-sw3-6.7b模型在2023年11月19日的评测结果，覆盖了ARC、HellaSwag、MMLU、TruthfulQA、Winogrande、DROP和GSM8K等涵盖常识推理、知识理解、数学计算与文本理解的多样化任务。作为瑞典语大模型gpt-sw3系列的代表，该模型在开放评测中的表现不仅反映了非英语语言模型在多任务泛化能力上的探索，也为多语言LLM的公平对比提供了重要参照，推动了评测生态的透明化与标准化。

当前挑战

该数据集所反映的核心挑战集中于多维度性能的均衡性。在领域问题层面，gpt-sw3-6.7b在Winogrande任务上取得了60.69%的准确率，显示出对代词消解与常识推理的基本掌握，但在GSM8K数学推理任务中仅达到0.53%的准确率，揭示了大型模型在符号推理与多步计算上的显著短板。此外，MMLU的57项子任务中，多数准确率徘徊于20%至30%之间，表明模型在专业知识广度上的泛化能力亟待提升。在构建过程中，评测流程需协调64个独立配置与多样化的评估框架（如EleutherAI Harness），确保数据格式一致性、结果可复现性及跨任务可比性，同时对存储与加载效率提出高要求，构成了技术实现与资源管理的双重挑战。

常用场景

经典使用场景

该数据集专为评估瑞典语大语言模型gpt-sw3-6.7b在多样化自然语言理解任务上的表现而构建，涵盖ARC挑战集、HellaSwag常识推理、Winogrande指代消解、GSM8K数学推理以及涵盖57个学科的大规模多任务语言理解基准（MMLU）等经典评测场景。研究者可便捷地通过HuggingFace Datasets库加载各任务的细粒度结果，复现模型在零样本或少样本设置下的推理能力，从而系统性地剖析模型在知识问答、常识推理与数学求解等维度的性能边界。

实际应用

在实际应用中，该数据集为瑞典语自然语言处理系统的选型与优化提供了量化决策依据。企业或研究机构可依据模型在Winogrande（指代消解）与HellaSwag（常识推理）上的表现，评估其在智能客服、文档理解等场景中的可靠性；而GSM8K与DROP的评分则直接映射了模型在金融计算、教育辅导等需要精确数值推理的工业场景中的适用性。该数据集因此成为连接模型学术评测与产业落地的关键桥梁。

衍生相关工作

基于该评测数据，衍生了一系列针对瑞典语大模型的诊断分析与改进工作。研究者利用其细粒度结果，对比分析了gpt-sw3系列不同参数量版本的性能差异，并据此提出了针对低资源语言模型的领域自适应微调策略。此外，该数据集催生了面向北欧语言的模型竞技排行榜，推动了包括指令微调、检索增强生成等技术在瑞典语场景中的验证与创新，成为该语言模型社区迭代演进的重要参照基准。