open-llm-leaderboard-old/details_KnutJaegersberg__webMistral-7B
收藏数据集概述
数据集摘要
该数据集是在评估模型 KnutJaegersberg/webMistral-7B 在 Open LLM Leaderboard 上的运行过程中自动创建的。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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。"train" 分割始终指向最新结果。
数据集结构
数据集包含以下配置：
- harness_arc_challenge_25
- harness_drop_3
- harness_gsm8k_5
- harness_hellaswag_10
- harness_hendrycksTest_5
每个配置包含多个数据文件，分为不同的分割（如 2023_11_19T15_44_56.176634 和 latest），每个分割对应一个或多个数据文件路径。
最新结果
以下是 2023-11-19T15:44:56.176634 运行 的最新结果：
python { "all": { "acc": 0.5841590014890155, "acc_stderr": 0.03333753951949392, "acc_norm": 0.5936832280847818, "acc_norm_stderr": 0.03411324688283648, "mc1": 0.2668298653610771, "mc1_stderr": 0.015483691939237272, "mc2": 0.397102297699568, "mc2_stderr": 0.014419759087988877, "em": 0.001363255033557047, "em_stderr": 0.0003778609196460787, "f1": 0.05746224832214775, "f1_stderr": 0.0013324273038450888 }, "harness|arc:challenge|25": { "acc": 0.53839590443686, "acc_stderr": 0.014568245550296356, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.014370358632472446 }, "harness|hellaswag|10": { "acc": 0.6154152559251145, "acc_stderr": 0.004855027248398159, "acc_norm": 0.8089026090420235, "acc_norm_stderr": 0.003923620666711542 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.039105257528497236, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.039105257528497236 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6415094339622641, "acc_stderr": 0.029514703583981762, "acc_norm": 0.6415094339622641, "acc_norm_stderr": 0.029514703583981762 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6666666666666666, "acc_stderr": 0.03942082639927213, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.03942082639927213 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.037038511930995215, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.037038511930995215 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5106382978723404, "acc_stderr": 0.03267862331014063, "acc_norm": 0.5106382978723404, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159795, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159795 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147125, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147125 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6967741935483871, "acc_stderr": 0.02614868593067175, "acc_norm": 0.6967741935483871, "acc_norm_stderr": 0.02614868593067175 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.46798029556650245, "acc_stderr": 0.035107665979592154, "acc_norm": 0.46798029556650245, "acc_norm_stderr": 0.035107665979592154 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.696969696969697, "acc_stderr": 0.03588624800091706, "acc_norm": 0.696969696969697, "acc_norm_stderr": 0.03588624800091706 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586818, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586818 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164552, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164552 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5846153846153846, "acc_stderr": 0.024985354923102346, "acc_norm": 0.5846153846153846, "acc_norm_stderr": 0.024985354923102346 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr":
