open-llm-leaderboard-old/details_PulsarAI__Draco-8x7B

--- pretty_name: Evaluation run of Weyaxi/Draco-8x7B dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [Weyaxi/Draco-8x7B](https://huggingface.co/Weyaxi/Draco-8x7B) on the [Open\ \ LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 63 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_Weyaxi__Draco-8x7B\"\ ,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\ These are the [latest results from run 2024-01-25T06:52:14.231942](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Draco-8x7B/blob/main/results_2024-01-25T06-52-14.231942.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\": 0.6523117174425681,\n\ \ \"acc_stderr\": 0.031872005741893215,\n \"acc_norm\": 0.6530656365171571,\n\ \ \"acc_norm_stderr\": 0.03252074448359809,\n \"mc1\": 0.4528763769889841,\n\ \ \"mc1_stderr\": 0.01742558984831402,\n \"mc2\": 0.6265250771231468,\n\ \ \"mc2_stderr\": 0.015246664453677405\n },\n \"harness|arc:challenge|25\"\ : {\n \"acc\": 0.6228668941979523,\n \"acc_stderr\": 0.014163366896192596,\n\ \ \"acc_norm\": 0.6501706484641638,\n \"acc_norm_stderr\": 0.013936809212158294\n\ \ },\n \"harness|hellaswag|10\": {\n \"acc\": 0.6653057159928301,\n\ \ \"acc_stderr\": 0.004709190850274406,\n \"acc_norm\": 0.8524198366859191,\n\ \ \"acc_norm_stderr\": 0.003539584491392116\n },\n \"harness|hendrycksTest-abstract_algebra|5\"\ : {\n \"acc\": 0.33,\n \"acc_stderr\": 0.04725815626252606,\n \ \ \"acc_norm\": 0.33,\n \"acc_norm_stderr\": 0.04725815626252606\n \ \ },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.6518518518518519,\n\ \ \"acc_stderr\": 0.041153246103369526,\n \"acc_norm\": 0.6518518518518519,\n\ \ \"acc_norm_stderr\": 0.041153246103369526\n },\n \"harness|hendrycksTest-astronomy|5\"\ : {\n \"acc\": 0.6973684210526315,\n \"acc_stderr\": 0.037385206761196686,\n\ \ \"acc_norm\": 0.6973684210526315,\n \"acc_norm_stderr\": 0.037385206761196686\n\ \ },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.64,\n\ \ \"acc_stderr\": 0.04824181513244218,\n \"acc_norm\": 0.64,\n \ \ \"acc_norm_stderr\": 0.04824181513244218\n },\n \"harness|hendrycksTest-clinical_knowledge|5\"\ : {\n \"acc\": 0.720754716981132,\n \"acc_stderr\": 0.027611163402399715,\n\ \ \"acc_norm\": 0.720754716981132,\n \"acc_norm_stderr\": 0.027611163402399715\n\ \ },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.7361111111111112,\n\ \ \"acc_stderr\": 0.03685651095897532,\n \"acc_norm\": 0.7361111111111112,\n\ \ \"acc_norm_stderr\": 0.03685651095897532\n },\n \"harness|hendrycksTest-college_chemistry|5\"\ : {\n \"acc\": 0.44,\n \"acc_stderr\": 0.04988876515698589,\n \ \ \"acc_norm\": 0.44,\n \"acc_norm_stderr\": 0.04988876515698589\n \ \ },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\"\ : 0.52,\n \"acc_stderr\": 0.050211673156867795,\n \"acc_norm\": 0.52,\n\ \ \"acc_norm_stderr\": 0.050211673156867795\n },\n \"harness|hendrycksTest-college_mathematics|5\"\ : {\n \"acc\": 0.33,\n \"acc_stderr\": 0.04725815626252604,\n \ \ \"acc_norm\": 0.33,\n \"acc_norm_stderr\": 0.04725815626252604\n \ \ },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.6878612716763006,\n\ \ \"acc_stderr\": 0.03533133389323657,\n \"acc_norm\": 0.6878612716763006,\n\ \ \"acc_norm_stderr\": 0.03533133389323657\n },\n \"harness|hendrycksTest-college_physics|5\"\ : {\n \"acc\": 0.4019607843137255,\n \"acc_stderr\": 0.048786087144669955,\n\ \ \"acc_norm\": 0.4019607843137255,\n \"acc_norm_stderr\": 0.048786087144669955\n\ \ },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\":\ \ 0.78,\n \"acc_stderr\": 0.04163331998932263,\n \"acc_norm\": 0.78,\n\ \ \"acc_norm_stderr\": 0.04163331998932263\n },\n \"harness|hendrycksTest-conceptual_physics|5\"\ : {\n \"acc\": 0.5829787234042553,\n \"acc_stderr\": 0.03223276266711712,\n\ \ \"acc_norm\": 0.5829787234042553,\n \"acc_norm_stderr\": 0.03223276266711712\n\ \ },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.47368421052631576,\n\ \ \"acc_stderr\": 0.046970851366478626,\n \"acc_norm\": 0.47368421052631576,\n\ \ \"acc_norm_stderr\": 0.046970851366478626\n },\n \"harness|hendrycksTest-electrical_engineering|5\"\ : {\n \"acc\": 0.5862068965517241,\n \"acc_stderr\": 0.04104269211806232,\n\ \ \"acc_norm\": 0.5862068965517241,\n \"acc_norm_stderr\": 0.04104269211806232\n\ \ },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\"\ : 0.3941798941798942,\n \"acc_stderr\": 0.02516798233389414,\n \"\ acc_norm\": 0.3941798941798942,\n \"acc_norm_stderr\": 0.02516798233389414\n\ \ },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.46825396825396826,\n\ \ \"acc_stderr\": 0.04463112720677172,\n \"acc_norm\": 0.46825396825396826,\n\ \ \"acc_norm_stderr\": 0.04463112720677172\n },\n \"harness|hendrycksTest-global_facts|5\"\ : {\n \"acc\": 0.37,\n \"acc_stderr\": 0.04852365870939099,\n \ \ \"acc_norm\": 0.37,\n \"acc_norm_stderr\": 0.04852365870939099\n \ \ },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.7838709677419354,\n\ \ \"acc_stderr\": 0.02341529343356852,\n \"acc_norm\": 0.7838709677419354,\n\ \ \"acc_norm_stderr\": 0.02341529343356852\n },\n \"harness|hendrycksTest-high_school_chemistry|5\"\ : {\n \"acc\": 0.4827586206896552,\n \"acc_stderr\": 0.035158955511657,\n\ \ \"acc_norm\": 0.4827586206896552,\n \"acc_norm_stderr\": 0.035158955511657\n\ \ },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \ \ \"acc\": 0.7,\n \"acc_stderr\": 0.046056618647183814,\n \"acc_norm\"\ : 0.7,\n \"acc_norm_stderr\": 0.046056618647183814\n },\n \"harness|hendrycksTest-high_school_european_history|5\"\ : {\n \"acc\": 0.7878787878787878,\n \"acc_stderr\": 0.03192271569548301,\n\ \ \"acc_norm\": 0.7878787878787878,\n \"acc_norm_stderr\": 0.03192271569548301\n\ \ },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\"\ : 0.7828282828282829,\n \"acc_stderr\": 0.029376616484945633,\n \"\ acc_norm\": 0.7828282828282829,\n \"acc_norm_stderr\": 0.029376616484945633\n\ \ },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n\ \ \"acc\": 0.8808290155440415,\n \"acc_stderr\": 0.023381935348121437,\n\ \ \"acc_norm\": 0.8808290155440415,\n \"acc_norm_stderr\": 0.023381935348121437\n\ \ },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \ \ \"acc\": 0.6692307692307692,\n \"acc_stderr\": 0.02385479568097112,\n \ \ \"acc_norm\": 0.6692307692307692,\n \"acc_norm_stderr\": 0.02385479568097112\n\ \ },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"\ acc\": 0.3592592592592593,\n \"acc_stderr\": 0.029252905927251972,\n \ \ \"acc_norm\": 0.3592592592592593,\n \"acc_norm_stderr\": 0.029252905927251972\n\ \ },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \ \ \"acc\": 0.6848739495798319,\n \"acc_stderr\": 0.030176808288974337,\n\ \ \"acc_norm\": 0.6848739495798319,\n \"acc_norm_stderr\": 0.030176808288974337\n\ \ },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\"\ : 0.3576158940397351,\n \"acc_stderr\": 0.03913453431177258,\n \"\ acc_norm\": 0.3576158940397351,\n \"acc_norm_stderr\": 0.03913453431177258\n\ \ },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\"\ : 0.8477064220183487,\n \"acc_stderr\": 0.015405084393157074,\n \"\ acc_norm\": 0.8477064220183487,\n \"acc_norm_stderr\": 0.015405084393157074\n\ \ },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\"\ : 0.5324074074074074,\n \"acc_stderr\": 0.03402801581358966,\n \"\ acc_norm\": 0.5324074074074074,\n \"acc_norm_stderr\": 0.03402801581358966\n\ \ },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\"\ : 0.8529411764705882,\n \"acc_stderr\": 0.024857478080250458,\n \"\ acc_norm\": 0.8529411764705882,\n \"acc_norm_stderr\": 0.024857478080250458\n\ \ },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"\ acc\": 0.810126582278481,\n \"acc_stderr\": 0.025530100460233504,\n \ \ \"acc_norm\": 0.810126582278481,\n \"acc_norm_stderr\": 0.025530100460233504\n\ \ },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.695067264573991,\n\ \ \"acc_stderr\": 0.030898610882477515,\n \"acc_norm\": 0.695067264573991,\n\ \ \"acc_norm_stderr\": 0.030898610882477515\n },\n \"harness|hendrycksTest-human_sexuality|5\"\ : {\n \"acc\": 0.7709923664122137,\n \"acc_stderr\": 0.036853466317118506,\n\ \ \"acc_norm\": 0.7709923664122137,\n \"acc_norm_stderr\": 0.036853466317118506\n\ \ },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\":\ \ 0.8347107438016529,\n \"acc_stderr\": 0.03390780612972776,\n \"\ acc_norm\": 0.8347107438016529,\n \"acc_norm_stderr\": 0.03390780612972776\n\ \ },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.7777777777777778,\n\ \ \"acc_stderr\": 0.040191074725573483,\n \"acc_norm\": 0.7777777777777778,\n\ \ \"acc_norm_stderr\": 0.040191074725573483\n },\n \"harness|hendrycksTest-logical_fallacies|5\"\ : {\n \"acc\": 0.8098159509202454,\n \"acc_stderr\": 0.03083349114628123,\n\ \ \"acc_norm\": 0.8098159509202454,\n \"acc_norm_stderr\": 0.03083349114628123\n\ \ },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.48214285714285715,\n\ \ \"acc_stderr\": 0.047427623612430116,\n \"acc_norm\": 0.48214285714285715,\n\ \ \"acc_norm_stderr\": 0.047427623612430116\n },\n \"harness|hendrycksTest-management|5\"\ : {\n \"acc\": 0.8349514563106796,\n \"acc_stderr\": 0.036756688322331886,\n\ \ \"acc_norm\": 0.8349514563106796,\n \"acc_norm_stderr\": 0.036756688322331886\n\ \ },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.8717948717948718,\n\ \ \"acc_stderr\": 0.02190190511507332,\n \"acc_norm\": 0.8717948717948718,\n\ \ \"acc_norm_stderr\": 0.02190190511507332\n },\n \"harness|hendrycksTest-medical_genetics|5\"\ : {\n \"acc\": 0.74,\n \"acc_stderr\": 0.0440844002276808,\n \ \ \"acc_norm\": 0.74,\n \"acc_norm_stderr\": 0.0440844002276808\n },\n\ \ \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.8250319284802043,\n\ \ \"acc_stderr\": 0.01358661921990334,\n \"acc_norm\": 0.8250319284802043,\n\ \ \"acc_norm_stderr\": 0.01358661921990334\n },\n \"harness|hendrycksTest-moral_disputes|5\"\ : {\n \"acc\": 0.7341040462427746,\n \"acc_stderr\": 0.02378620325550829,\n\ \ \"acc_norm\": 0.7341040462427746,\n \"acc_norm_stderr\": 0.02378620325550829\n\ \ },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.2860335195530726,\n\ \ \"acc_stderr\": 0.015113972129062136,\n \"acc_norm\": 0.2860335195530726,\n\ \ \"acc_norm_stderr\": 0.015113972129062136\n },\n \"harness|hendrycksTest-nutrition|5\"\ : {\n \"acc\": 0.7320261437908496,\n \"acc_stderr\": 0.025360603796242557,\n\ \ \"acc_norm\": 0.7320261437908496,\n \"acc_norm_stderr\": 0.025360603796242557\n\ \ },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.7041800643086816,\n\ \ \"acc_stderr\": 0.02592237178881877,\n \"acc_norm\": 0.7041800643086816,\n\ \ \"acc_norm_stderr\": 0.02592237178881877\n },\n \"harness|hendrycksTest-prehistory|5\"\ : {\n \"acc\": 0.7530864197530864,\n \"acc_stderr\": 0.0239935017090421,\n\ \ \"acc_norm\": 0.7530864197530864,\n \"acc_norm_stderr\": 0.0239935017090421\n\ \ },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"\ acc\": 0.5141843971631206,\n \"acc_stderr\": 0.02981549448368206,\n \ \ \"acc_norm\": 0.5141843971631206,\n \"acc_norm_stderr\": 0.02981549448368206\n\ \ },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.4641460234680574,\n\ \ \"acc_stderr\": 0.01273736131873058,\n \"acc_norm\": 0.4641460234680574,\n\ \ \"acc_norm_stderr\": 0.01273736131873058\n },\n \"harness|hendrycksTest-professional_medicine|5\"\ : {\n \"acc\": 0.6985294117647058,\n \"acc_stderr\": 0.027875982114273168,\n\ \ \"acc_norm\": 0.6985294117647058,\n \"acc_norm_stderr\": 0.027875982114273168\n\ \ },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"\ acc\": 0.6699346405228758,\n \"acc_stderr\": 0.019023726160724553,\n \ \ \"acc_norm\": 0.6699346405228758,\n \"acc_norm_stderr\": 0.019023726160724553\n\ \ },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.6363636363636364,\n\ \ \"acc_stderr\": 0.046075820907199756,\n \"acc_norm\": 0.6363636363636364,\n\ \ \"acc_norm_stderr\": 0.046075820907199756\n },\n \"harness|hendrycksTest-security_studies|5\"\ : {\n \"acc\": 0.7387755102040816,\n \"acc_stderr\": 0.028123429335142773,\n\ \ \"acc_norm\": 0.7387755102040816,\n \"acc_norm_stderr\": 0.028123429335142773\n\ \ },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8407960199004975,\n\ \ \"acc_stderr\": 0.02587064676616913,\n \"acc_norm\": 0.8407960199004975,\n\ \ \"acc_norm_stderr\": 0.02587064676616913\n },\n \"harness|hendrycksTest-us_foreign_policy|5\"\ : {\n \"acc\": 0.88,\n \"acc_stderr\": 0.03265986323710906,\n \ \ \"acc_norm\": 0.88,\n \"acc_norm_stderr\": 0.03265986323710906\n \ \ },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.5481927710843374,\n\ \ \"acc_stderr\": 0.03874371556587953,\n \"acc_norm\": 0.5481927710843374,\n\ \ \"acc_norm_stderr\": 0.03874371556587953\n },\n \"harness|hendrycksTest-world_religions|5\"\ : {\n \"acc\": 0.8421052631578947,\n \"acc_stderr\": 0.027966785859160882,\n\ \ \"acc_norm\": 0.8421052631578947,\n \"acc_norm_stderr\": 0.027966785859160882\n\ \ },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.4528763769889841,\n\ \ \"mc1_stderr\": 0.01742558984831402,\n \"mc2\": 0.6265250771231468,\n\ \ \"mc2_stderr\": 0.015246664453677405\n },\n \"harness|winogrande|5\"\ : {\n \"acc\": 0.8066298342541437,\n \"acc_stderr\": 0.011099796645920526\n\ \ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.6679302501895376,\n \ \ \"acc_stderr\": 0.012972465034361861\n }\n}\n```" repo_url: https://huggingface.co/Weyaxi/Draco-8x7B 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: 2024_01_25T06_52_14.231942 path: - '**/details_harness|arc:challenge|25_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|arc:challenge|25_2024-01-25T06-52-14.231942.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|gsm8k|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hellaswag_10 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hellaswag|10_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hellaswag|10_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-international_law|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-management|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-marketing|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-sociology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-virology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-anatomy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-astronomy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-business_ethics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_biology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_chemistry|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_computer_science|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_medicine|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-college_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-computer_security|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-econometrics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-formal_logic|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-global_facts|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_biology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_geography|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_physics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-human_aging|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-human_sexuality|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-international_law|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-jurisprudence|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-machine_learning|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-management|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-marketing|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-medical_genetics|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-miscellaneous|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-moral_disputes|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-nutrition|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-philosophy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-prehistory|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_accounting|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_law|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_medicine|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-professional_psychology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-public_relations|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-security_studies|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-sociology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-virology|5_2024-01-25T06-52-14.231942.parquet' - '**/details_harness|hendrycksTest-world_religions|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_abstract_algebra_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-abstract_algebra|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_anatomy_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-anatomy|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-anatomy|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_astronomy_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-astronomy|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-astronomy|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_business_ethics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-business_ethics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-business_ethics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_clinical_knowledge_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_biology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_biology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_biology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_chemistry_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_chemistry|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_chemistry|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_computer_science_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_computer_science|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_computer_science|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_mathematics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_mathematics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_mathematics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_medicine_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_medicine|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_medicine|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_college_physics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-college_physics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-college_physics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_computer_security_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-computer_security|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-computer_security|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_conceptual_physics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-conceptual_physics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_econometrics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-econometrics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-econometrics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_electrical_engineering_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-electrical_engineering|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_elementary_mathematics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_formal_logic_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-formal_logic|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-formal_logic|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_global_facts_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-global_facts|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-global_facts|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_biology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_biology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_biology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_chemistry_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_computer_science_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_computer_science|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_european_history_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_european_history|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_geography_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_geography|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_geography|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_government_and_politics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_macroeconomics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_mathematics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_mathematics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_microeconomics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_physics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_physics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_physics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_psychology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_psychology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_statistics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_statistics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_us_history_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_us_history|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_high_school_world_history_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-high_school_world_history|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_human_aging_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-human_aging|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_aging|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_human_sexuality_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-human_sexuality|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-human_sexuality|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_international_law_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-international_law|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-international_law|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_jurisprudence_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-jurisprudence|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-jurisprudence|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_logical_fallacies_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-logical_fallacies|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_machine_learning_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-machine_learning|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-machine_learning|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_management_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-management|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-management|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_marketing_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-marketing|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-marketing|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_medical_genetics_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-medical_genetics|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-medical_genetics|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_miscellaneous_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-miscellaneous|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-miscellaneous|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_moral_disputes_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-moral_disputes|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_disputes|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_moral_scenarios_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-moral_scenarios|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_nutrition_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-nutrition|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-nutrition|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_philosophy_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-philosophy|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-philosophy|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_prehistory_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-prehistory|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-prehistory|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_professional_accounting_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-professional_accounting|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_accounting|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_professional_law_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-professional_law|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_law|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_professional_medicine_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-professional_medicine|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_medicine|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_professional_psychology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-professional_psychology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-professional_psychology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_public_relations_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-public_relations|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-public_relations|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_security_studies_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-security_studies|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-security_studies|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_sociology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-sociology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-sociology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_us_foreign_policy_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-us_foreign_policy|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_virology_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-virology|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-virology|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_hendrycksTest_world_religions_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|hendrycksTest-world_religions|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|hendrycksTest-world_religions|5_2024-01-25T06-52-14.231942.parquet' - config_name: harness_truthfulqa_mc_0 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|truthfulqa:mc|0_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|truthfulqa:mc|0_2024-01-25T06-52-14.231942.parquet' - config_name: harness_winogrande_5 data_files: - split: 2024_01_25T06_52_14.231942 path: - '**/details_harness|winogrande|5_2024-01-25T06-52-14.231942.parquet' - split: latest path: - '**/details_harness|winogrande|5_2024-01-25T06-52-14.231942.parquet' - config_name: results data_files: - split: 2024_01_25T06_52_14.231942 path: - results_2024-01-25T06-52-14.231942.parquet - split: latest path: - results_2024-01-25T06-52-14.231942.parquet --- # Dataset Card for Evaluation run of Weyaxi/Draco-8x7B <!-- Provide a quick summary of the dataset. --> Dataset automatically created during the evaluation run of model [Weyaxi/Draco-8x7B](https://huggingface.co/Weyaxi/Draco-8x7B) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 63 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_Weyaxi__Draco-8x7B", "harness_winogrande_5", split="train") ``` ## Latest results These are the [latest results from run 2024-01-25T06:52:14.231942](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Draco-8x7B/blob/main/results_2024-01-25T06-52-14.231942.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": 0.6523117174425681, "acc_stderr": 0.031872005741893215, "acc_norm": 0.6530656365171571, "acc_norm_stderr": 0.03252074448359809, "mc1": 0.4528763769889841, "mc1_stderr": 0.01742558984831402, "mc2": 0.6265250771231468, "mc2_stderr": 0.015246664453677405 }, "harness|arc:challenge|25": { "acc": 0.6228668941979523, "acc_stderr": 0.014163366896192596, "acc_norm": 0.6501706484641638, "acc_norm_stderr": 0.013936809212158294 }, "harness|hellaswag|10": { "acc": 0.6653057159928301, "acc_stderr": 0.004709190850274406, "acc_norm": 0.8524198366859191, "acc_norm_stderr": 0.003539584491392116 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.037385206761196686, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.037385206761196686 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.03533133389323657, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.03533133389323657 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932263, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932263 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5829787234042553, "acc_stderr": 0.03223276266711712, "acc_norm": 0.5829787234042553, "acc_norm_stderr": 0.03223276266711712 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3941798941798942, "acc_stderr": 0.02516798233389414, "acc_norm": 0.3941798941798942, "acc_norm_stderr": 0.02516798233389414 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356852, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356852 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4827586206896552, "acc_stderr": 0.035158955511657, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.035158955511657 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548301, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.029376616484945633, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.029376616484945633 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121437, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121437 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6692307692307692, "acc_stderr": 0.02385479568097112, "acc_norm": 0.6692307692307692, "acc_norm_stderr": 0.02385479568097112 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251972, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0.029252905927251972 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6848739495798319, "acc_stderr": 0.030176808288974337, "acc_norm": 0.6848739495798319, "acc_norm_stderr": 0.030176808288974337 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3576158940397351, "acc_stderr": 0.03913453431177258, "acc_norm": 0.3576158940397351, "acc_norm_stderr": 0.03913453431177258 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8477064220183487, "acc_stderr": 0.015405084393157074, "acc_norm": 0.8477064220183487, "acc_norm_stderr": 0.015405084393157074 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5324074074074074, "acc_stderr": 0.03402801581358966, "acc_norm": 0.5324074074074074, "acc_norm_stderr": 0.03402801581358966 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.8529411764705882, "acc_stderr": 0.024857478080250458, "acc_norm": 0.8529411764705882, "acc_norm_stderr": 0.024857478080250458 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.810126582278481, "acc_stderr": 0.025530100460233504, "acc_norm": 0.810126582278481, "acc_norm_stderr": 0.025530100460233504 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.695067264573991, "acc_stderr": 0.030898610882477515, "acc_norm": 0.695067264573991, "acc_norm_stderr": 0.030898610882477515 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7709923664122137, "acc_stderr": 0.036853466317118506, "acc_norm": 0.7709923664122137, "acc_norm_stderr": 0.036853466317118506 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8347107438016529, "acc_stderr": 0.03390780612972776, "acc_norm": 0.8347107438016529, "acc_norm_stderr": 0.03390780612972776 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7777777777777778, "acc_stderr": 0.040191074725573483, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.040191074725573483 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.8098159509202454, "acc_stderr": 0.03083349114628123, "acc_norm": 0.8098159509202454, "acc_norm_stderr": 0.03083349114628123 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.48214285714285715, "acc_stderr": 0.047427623612430116, "acc_norm": 0.48214285714285715, "acc_norm_stderr": 0.047427623612430116 }, "harness|hendrycksTest-management|5": { "acc": 0.8349514563106796, "acc_stderr": 0.036756688322331886, "acc_norm": 0.8349514563106796, "acc_norm_stderr": 0.036756688322331886 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8717948717948718, "acc_stderr": 0.02190190511507332, "acc_norm": 0.8717948717948718, "acc_norm_stderr": 0.02190190511507332 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8250319284802043, "acc_stderr": 0.01358661921990334, "acc_norm": 0.8250319284802043, "acc_norm_stderr": 0.01358661921990334 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7341040462427746, "acc_stderr": 0.02378620325550829, "acc_norm": 0.7341040462427746, "acc_norm_stderr": 0.02378620325550829 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.2860335195530726, "acc_stderr": 0.015113972129062136, "acc_norm": 0.2860335195530726, "acc_norm_stderr": 0.015113972129062136 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7320261437908496, "acc_stderr": 0.025360603796242557, "acc_norm": 0.7320261437908496, "acc_norm_stderr": 0.025360603796242557 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7041800643086816, "acc_stderr": 0.02592237178881877, "acc_norm": 0.7041800643086816, "acc_norm_stderr": 0.02592237178881877 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7530864197530864, "acc_stderr": 0.0239935017090421, "acc_norm": 0.7530864197530864, "acc_norm_stderr": 0.0239935017090421 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.5141843971631206, "acc_stderr": 0.02981549448368206, "acc_norm": 0.5141843971631206, "acc_norm_stderr": 0.02981549448368206 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4641460234680574, "acc_stderr": 0.01273736131873058, "acc_norm": 0.4641460234680574, "acc_norm_stderr": 0.01273736131873058 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6985294117647058, "acc_stderr": 0.027875982114273168, "acc_norm": 0.6985294117647058, "acc_norm_stderr": 0.027875982114273168 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6699346405228758, "acc_stderr": 0.019023726160724553, "acc_norm": 0.6699346405228758, "acc_norm_stderr": 0.019023726160724553 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6363636363636364, "acc_stderr": 0.046075820907199756, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.046075820907199756 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7387755102040816, "acc_stderr": 0.028123429335142773, "acc_norm": 0.7387755102040816, "acc_norm_stderr": 0.028123429335142773 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8407960199004975, "acc_stderr": 0.02587064676616913, "acc_norm": 0.8407960199004975, "acc_norm_stderr": 0.02587064676616913 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.88, "acc_stderr": 0.03265986323710906, "acc_norm": 0.88, "acc_norm_stderr": 0.03265986323710906 }, "harness|hendrycksTest-virology|5": { "acc": 0.5481927710843374, "acc_stderr": 0.03874371556587953, "acc_norm": 0.5481927710843374, "acc_norm_stderr": 0.03874371556587953 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8421052631578947, "acc_stderr": 0.027966785859160882, "acc_norm": 0.8421052631578947, "acc_norm_stderr": 0.027966785859160882 }, "harness|truthfulqa:mc|0": { "mc1": 0.4528763769889841, "mc1_stderr": 0.01742558984831402, "mc2": 0.6265250771231468, "mc2_stderr": 0.015246664453677405 }, "harness|winogrande|5": { "acc": 0.8066298342541437, "acc_stderr": 0.011099796645920526 }, "harness|gsm8k|5": { "acc": 0.6679302501895376, "acc_stderr": 0.012972465034361861 } } ``` ## Dataset Details ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> - **Curated by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] ### Dataset Sources [optional] <!-- Provide the basic links for the dataset. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the dataset is intended to be used. --> ### Direct Use <!-- This section describes suitable use cases for the dataset. --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> [More Information Needed] ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> [More Information Needed] ## Dataset Creation ### Curation Rationale <!-- Motivation for the creation of this dataset. --> [More Information Needed] ### Source Data <!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). --> #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> [More Information Needed] #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> [More Information Needed] ### Annotations [optional] <!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. --> #### Annotation process <!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. --> [More Information Needed] #### Who are the annotators? <!-- This section describes the people or systems who created the annotations. --> [More Information Needed] #### Personal and Sensitive Information <!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional] <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Dataset Card Authors [optional] [More Information Needed] ## Dataset Card Contact [More Information Needed]

原始信息汇总

数据集概述

数据集简介

该数据集是在模型 Weyaxi/Draco-8x7B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

数据集组成

• 数据集包含 63 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 "results" 配置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_Weyaxi__Draco-8x7B", "harness_winogrande_5", split="train")

最新结果

以下是 2024-01-25T06:52:14.231942 运行的最新结果：

python { "all": { "acc": 0.6523117174425681, "acc_stderr": 0.031872005741893215, "acc_norm": 0.6530656365171571, "acc_norm_stderr": 0.03252074448359809, "mc1": 0.4528763769889841, "mc1_stderr": 0.01742558984831402, "mc2": 0.6265250771231468, "mc2_stderr": 0.015246664453677405 }, "harness|arc:challenge|25": { "acc": 0.6228668941979523, "acc_stderr": 0.014163366896192596, "acc_norm": 0.6501706484641638, "acc_norm_stderr": 0.013936809212158294 }, "harness|hellaswag|10": { "acc": 0.6653057159928301, "acc_stderr": 0.004709190850274406, "acc_norm": 0.8524198366859191, "acc_norm_stderr": 0.003539584491392116 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, ... }

配置详情

• config_name: harness_arc_challenge_25

  • 分割: 2024_01_25T06_52_14.231942
    • 路径: **/details_harness|arc:challenge|25_2024-01-25T06-52-14.231942.parquet
  • 分割: latest
    • 路径: **/details_harness|arc:challenge|25_2024-01-25T06-52-14.231942.parquet

• config_name: harness_gsm8k_5

  • 分割: 2024_01_25T06_52_14.231942
    • 路径: **/details_harness|gsm8k|5_2024-01-25T06-52-14.231942.parquet
  • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2024-01-25T06-52-14.231942.parquet

• config_name: harness_hellaswag_10

  • 分割: 2024_01_25T06_52_14.231942
    • 路径: **/details_harness|hellaswag|10_2024-01-25T06-52-14.231942.parquet
  • 分割: latest
    • 路径: **/details_harness|hellaswag|10_2024-01-25T06-52-14.231942.parquet

• config_name: harness_hendrycksTest_5

  • 分割: 2024_01_25T06_52_14.231942
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-01-25T06-52-14.231942.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-25T06-52-14.231942.parquet
      • ... }

搜集汇总

数据集介绍

构建方式

在大语言模型评测领域，Open LLM Leaderboard 作为一个权威的基准平台，为模型性能的横向对比提供了标准化框架。该数据集正是为记录模型 Weyaxi/Draco-8x7B 在 Leaderboard 上的评估过程而自动生成的。其构建方式基于单一评估运行，共涵盖 63 个配置，每个配置对应一个被评估的具体任务。每次运行的评估结果均以时间戳命名，作为该配置下的独立分割（split），而“train”分割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，用于存储所有聚合后的评估指标，这些指标正是 Leaderboard 上展示的最终分数来源。

特点

该数据集的核心特色在于其结构化的多任务覆盖能力与版本追溯机制。它囊括了从常识推理（如 ARC-Challenge、HellaSwag）到数学推理（如 GSM8K）、从专业知识（如 MMLU 的 57 个学科子集）到对抗性问答（如 TruthfulQA）等广泛任务，为模型能力的细粒度剖析提供了丰富素材。每个任务的配置均独立存储，且通过时间戳分割保留了每一次评估的历史快照，使得研究者可以回溯模型性能的演进轨迹。这种设计不仅便于横向对比不同任务的得分，还能纵向追踪同一模型在多次评估中的稳定性与变化。

使用方法

研究人员可通过 HuggingFace 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（如 `open-llm-leaderboard/details_Weyaxi__Draco-8x7B`）及所需的任务配置名称（例如 `harness_winogrande_5`）即可获取对应任务的评估细节。通过设置 `split` 参数为 `"train"` 可获取最新评估结果，或指定具体时间戳（如 `"2024_01_25T06_52_14.231942"`）来加载历史数据。加载后的数据以 Parquet 格式存储，便于高效处理和分析，适用于模型性能复现、误差分析以及多维度指标的可视化展示。

背景与挑战

背景概述

随着大规模语言模型（LLMs）的蓬勃发展，如何公正、全面地评估其性能成为自然语言处理领域的关键议题。Hugging Face社区推出的Open LLM Leaderboard为此提供了标准化评测平台，而本数据集正是该平台对Weyaxi团队研发的Draco-8x7B模型进行自动化评估的产物。该数据集创建于2024年1月，由Hugging Face的Clementine等人主导，围绕63个评测任务（涵盖ARC挑战赛、HellaSwag、GSM8K、MMLU及TruthfulQA等）记录模型表现。其核心研究问题在于量化Draco-8x7B在多维度推理、知识理解与安全性上的综合能力，为开源社区的模型对比与迭代提供透明、可复现的基准。该数据集作为Open LLM Leaderboard的组成部分，通过标准化流程赋能研究者洞察模型优劣，推动了LLM评估体系的规范化进程。

当前挑战

该数据集所涉领域挑战集中于LLM评估的全面性与公平性：Draco-8x7B需在63个异构任务中展现均衡能力，如ARC挑战赛（准确率62.29%）与GSM8K数学推理（66.79%）的差异表明模型在符号推理与常识理解间的权衡难题。此外，构建过程面临多维挑战：一是任务整合的复杂性，需统一格式并确保57个MMLU子任务、Winogrande等评测的兼容性；二是结果可复现性，需通过parquet文件与时间戳分片管理多次运行的细节，避免数据混淆；三是标准化指标计算，如acc_norm与mc2的统计需消除采样偏差，这对存储与解析逻辑提出严苛要求。这些挑战共同凸显了在大规模自动化评测中实现精准与透明的不易。

常用场景

经典使用场景

在大型语言模型（LLM）的评估生态中，Open LLM Leaderboard 详情数据集为 Draco-8x7B 等模型提供了标准化的性能基准测试平台。该数据集涵盖了包括 ARC-Challenge、HellaSwag、MMLU（涵盖 57 个学科）、TruthfulQA、Winogrande 和 GSM8K 在内的 63 项经典自然语言理解与推理任务。每一配置对应一项评估任务，记录模型在零样本或少样本设定下的准确率、标准化准确率及误差范围。研究者通过加载各任务的 Parquet 格式数据，可深入剖析模型在常识推理、数学问题求解、知识问答及对抗性文本检测等维度的表现，从而实现对模型能力的全面诊断与横向对比。

解决学术问题

该数据集系统性地解决了 LLM 评估中缺乏统一、细粒度评测基准的学术难题。长期以来，不同研究团队采用各异的数据集与评估协议，导致模型性能难以公平比较。此数据集通过整合多维度任务（如 MMLU 的跨学科知识、GSM8K 的数学推理、TruthfulQA 的诚实性检测），为学术界提供了标准化的评估框架。其意义在于：一方面，揭示了模型在特定领域（如高等数学、法律、医学）的薄弱环节，推动针对性改进；另一方面，通过记录多次运行结果与统计误差，增强了评估的统计稳健性，为模型迭代与理论验证提供了可靠依据。

衍生相关工作

此数据集衍生了一系列影响深远的经典工作。基于其评估框架，研究者提出了多项改进方案：如通过对比同一模型在不同时间戳运行的结果，分析训练稳定性与数据顺序影响；利用 MMLU 的子任务得分，开发出针对特定学科的知识增强技术。此外，该数据集催生了 Open LLM Leaderboard 这一动态排行榜，成为衡量模型进步的风向标。后续工作如 FLAN、T0 等模型在微调策略上的突破，均参考了本数据集的评估体系。其 Parquet 格式的高效存储与加载方式，也为大规模评估数据的标准化管理树立了典范。