open-llm-leaderboard-old/details_JaeyeonKang__CCK_gony

该数据集是在Open LLM Leaderboard上对模型JaeyeonKang/CCK_gony进行评估时自动生成的。数据集由63个配置组成，每个配置对应一个评估任务。它包含一次运行的数据，每次运行在每个配置中表示为特定的分割，分割名称由运行的时间戳命名。train分割始终指向最新结果。一个名为results的额外配置存储了所有运行的聚合结果，用于在Open LLM Leaderboard上计算和显示聚合指标。README还提供了加载数据集详细信息的Python代码片段，并列出了特定运行的最新结果。

原始信息汇总

数据集概述

该数据集是在对模型 JaeyeonKang/CCK_gony 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。

最新结果

以下是 2024-01-24T11:01:11.626042 运行的最新结果：

python { "all": { "acc": 0.6924973006675793, "acc_stderr": 0.030756010778234835, "acc_norm": 0.6971433352879666, "acc_norm_stderr": 0.031350039645753676, "mc1": 0.41615667074663404, "mc1_stderr": 0.017255657502903043, "mc2": 0.5674014937456792, "mc2_stderr": 0.015092873937221477 }, "harness|arc:challenge|25": { "acc": 0.6382252559726962, "acc_stderr": 0.014041957945038082, "acc_norm": 0.6911262798634812, "acc_norm_stderr": 0.013501770929344 }, "harness|hellaswag|10": { "acc": 0.6756622186815375, "acc_stderr": 0.004671701705567238, "acc_norm": 0.867755427205736, "acc_norm_stderr": 0.003380641470989921 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.41, "acc_stderr": 0.04943110704237103, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237103 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7828947368421053, "acc_stderr": 0.03355045304882923, "acc_norm": 0.7828947368421053, "acc_norm_stderr": 0.03355045304882923 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.769811320754717, "acc_stderr": 0.025907897122408173, "acc_norm": 0.769811320754717, "acc_norm_stderr": 0.025907897122408173 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8402777777777778, "acc_stderr": 0.03063557897209328, "acc_norm": 0.8402777777777778, "acc_norm_stderr": 0.03063557897209328 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7109826589595376, "acc_stderr": 0.034564257450869995, "acc_norm": 0.7109826589595376, "acc_norm_stderr": 0.034564257450869995 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6510638297872341, "acc_stderr": 0.031158522131357783, "acc_norm": 0.6510638297872341, "acc_norm_stderr": 0.031158522131357783 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5701754385964912, "acc_stderr": 0.04657047260594964, "acc_norm": 0.5701754385964912, "acc_norm_stderr": 0.04657047260594964 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6689655172413793, "acc_stderr": 0.03921545312467122, "acc_norm": 0.6689655172413793, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4497354497354497, "acc_stderr": 0.02562085704293665, "acc_norm": 0.4497354497354497, "acc_norm_stderr": 0.02562085704293665 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5079365079365079, "acc_stderr": 0.044715725362943486, "acc_norm": 0.5079365079365079, "acc_norm_stderr": 0.044715725362943486 }, "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": 0.8096774193548387, "acc_stderr": 0.02233170761182307, "acc_norm": 0.8096774193548387, "acc_norm_stderr": 0.02233170761182307 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5566502463054187, "acc_stderr": 0.03495334582162933, "acc_norm": 0.5566502463054187, "acc_norm_stderr": 0.03495334582162933 }, "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": 0.793939393939394, "acc_stderr": 0.03158415324047709, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.03158415324047709 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8434343434343434, "acc_stderr": 0.025890520358141454, "acc_norm": 0.8434343434343434, "acc_norm_stderr": 0.025890520358141454 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.927461139896373, "acc_stderr": 0.018718998520678178, "acc_norm": 0.927461139896373, "acc_norm_stderr": 0.018718998520678178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7025641025641025, "acc_stderr": 0.023177408131465953, "acc_norm": 0.7025641025641025, "acc_norm_stderr": 0.023177408131465953 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37407407407407406, "acc_stderr": 0.029502861128955293, "acc_norm": 0.37407407407407406, "acc_norm_stderr": 0.029502861128955293 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7647058823529411, "acc_stderr": 0.027