open-llm-leaderboard-old/details_itsliupeng__llama2_7b_zh

该数据集是在模型itsliupeng/llama2_7b_zh在Open LLM Leaderboard上的评估运行过程中自动创建的。数据集由64个配置组成，每个配置对应一个被评估的任务。数据集是从1次运行中创建的，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。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集组成

该数据集包含64个配置，每个配置对应一个评估任务。数据集是从1次运行中创建的，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。

额外配置

一个额外的配置"results"存储了所有运行的聚合结果，用于计算和显示在Open LLM Leaderboard上的聚合指标。

最新结果

以下是2023-11-15T10:51:37.128756运行的最新结果：

python { "all": { "acc": 0.5969511263414031, "acc_stderr": 0.0329865461490785, "acc_norm": 0.6078135521201408, "acc_norm_stderr": 0.03376504385445851, "mc1": 0.2766217870257038, "mc1_stderr": 0.015659605755326912, "mc2": 0.42858587749612026, "mc2_stderr": 0.014059235435250938, "em": 0.18791946308724833, "em_stderr": 0.004000599568072892, "f1": 0.23667890100671124, "f1_stderr": 0.003992615682814011 }, "harness|arc:challenge|25": { "acc": 0.47952218430034127, "acc_stderr": 0.01459913135303501, "acc_norm": 0.5204778156996587, "acc_norm_stderr": 0.01459913135303501 }, "harness|hellaswag|10": { "acc": 0.5608444532961562, "acc_stderr": 0.004952698802275648, "acc_norm": 0.7487552280422227, "acc_norm_stderr": 0.004328425700998689 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.042763494943765995, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.042763494943765995 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.03761070869867479, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.03761070869867479 }, "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": 0.6566037735849056, "acc_stderr": 0.029224526469124792, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.029224526469124792 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "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": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.0373362665538351, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.0373362665538351 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082634, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082634 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.548936170212766, "acc_stderr": 0.03252909619613197, "acc_norm": 0.548936170212766, "acc_norm_stderr": 0.03252909619613197 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.34210526315789475, "acc_stderr": 0.044629175353369355, "acc_norm": 0.34210526315789475, "acc_norm_stderr": 0.044629175353369355 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370333, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.025107425481137285, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.025107425481137285 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7064516129032258, "acc_stderr": 0.025906087021319295, "acc_norm": 0.7064516129032258, "acc_norm_stderr": 0.025906087021319295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386414, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386414 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.02649905770139744, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.02649905770139744 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5871794871794872, "acc_stderr": 0.024962683564331796, "acc_norm": 0.5871794871794872, "acc_norm_stderr": 0.024962683564331796 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.02822644674968352, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.02822644674968352 }, "harness|hendrycksTest-high_school_microeconomics|5": { "