open-llm-leaderboard-old/details_BarraHome__LLaMaRada-3-orpo-v2-8b

该数据集是在模型BarraHome/LLaMaRada-3-orpo-v2-8b在Open LLM Leaderboard上的评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。它包含1次运行的结果，每次运行都作为每个配置中的一个特定分割存储。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python中的datasets库加载数据集的示例。

原始信息汇总

数据集概述

该数据集是在对模型 BarraHome/LLaMaRada-3-orpo-v2-8b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

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，每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
• "train" 分割总是指向最新的结果。
• 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。

最新结果

以下是 2024-04-23T10:22:36.405138 运行的最新结果：

python { "all": { "acc": 0.6618808458167869, "acc_stderr": 0.03170817470547351, "acc_norm": 0.6674086629134086, "acc_norm_stderr": 0.0323305066048034, "mc1": 0.30966952264381886, "mc1_stderr": 0.016185744355144912, "mc2": 0.4766957476038386, "mc2_stderr": 0.014477503866545062 }, "harness|arc:challenge|25": { "acc": 0.5503412969283277, "acc_stderr": 0.014537144444284743, "acc_norm": 0.5989761092150171, "acc_norm_stderr": 0.014322255790719867 }, "harness|hellaswag|10": { "acc": 0.6202947619996017, "acc_stderr": 0.004843216325090257, "acc_norm": 0.8222465644293966, "acc_norm_stderr": 0.003815237269961105 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.039992628766177214, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395269, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395269 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7584905660377359, "acc_stderr": 0.02634148037111835, "acc_norm": 0.7584905660377359, "acc_norm_stderr": 0.02634148037111835 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.049665709039785295, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.049665709039785295 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6, "acc_stderr": 0.03202563076101737, "acc_norm": 0.6, "acc_norm_stderr": 0.03202563076101737 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6344827586206897, "acc_stderr": 0.04013124195424386, "acc_norm": 0.6344827586206897, "acc_norm_stderr": 0.04013124195424386 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.025446365634406772, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406772 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356853, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356853 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7696969696969697, "acc_stderr": 0.0328766675860349, "acc_norm": 0.7696969696969697, "acc_norm_stderr": 0.0328766675860349 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.028335609732463362, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.028335609732463362 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919436, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919436 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6538461538461539, "acc_stderr": 0.024121125416941183, "acc_norm": 0.6538461538461539, "acc_norm_stderr": 0.024121125416941183 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630886, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.029670906124630886 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.726890756302521, "acc_stderr": 0.0289420