open-llm-leaderboard-old/details_Taekyoon__llama2-ko-7b-test

该数据集是在Open LLM Leaderboard上对模型TaeKyoon/llama2-ko-7b-test进行评估时自动生成的。数据集由61个配置组成，每个配置对应一个被评估的任务。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还提供了一个Python代码片段用于加载数据集详细信息，并列出了特定运行的最新结果。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 Taekyoon/llama2-ko-7b-test 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 该数据集包含 61 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。
• 一个额外的配置 "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 2023-08-28T09:09:02.494936 运行的最新结果：

python { "all": { "acc": 0.29939516770443486, "acc_stderr": 0.03301601100044412, "acc_norm": 0.3025804071569399, "acc_norm_stderr": 0.03301705555289615, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023505, "mc2": 0.35997350772493825, "mc2_stderr": 0.014042588070598837 }, "harness|arc:challenge|25": { "acc": 0.3506825938566553, "acc_stderr": 0.013944635930726089, "acc_norm": 0.3779863481228669, "acc_norm_stderr": 0.014169664520303105 }, "harness|hellaswag|10": { "acc": 0.4697271459868552, "acc_stderr": 0.004980627287147587, "acc_norm": 0.6303525194184425, "acc_norm_stderr": 0.004817227292240292 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2518518518518518, "acc_stderr": 0.03749850709174022, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.03749850709174022 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3223684210526316, "acc_stderr": 0.03803510248351585, "acc_norm": 0.3223684210526316, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3320754716981132, "acc_stderr": 0.02898545565233439, "acc_norm": 0.3320754716981132, "acc_norm_stderr": 0.02898545565233439 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.24305555555555555, "acc_stderr": 0.03586879280080341, "acc_norm": 0.24305555555555555, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2774566473988439, "acc_stderr": 0.034140140070440354, "acc_norm": 0.2774566473988439, "acc_norm_stderr": 0.034140140070440354 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237657, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237657 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.044346007015849245, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.044346007015849245 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.022569897074918424, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.022569897074918424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.15079365079365079, "acc_stderr": 0.032006864972873916, "acc_norm": 0.15079365079365079, "acc_norm_stderr": 0.032006864972873916 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.23225806451612904, "acc_stderr": 0.02402225613030824, "acc_norm": 0.23225806451612904, "acc_norm_stderr": 0.02402225613030824 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.26108374384236455, "acc_stderr": 0.030903796952114485, "acc_norm": 0.26108374384236455, "acc_norm_stderr": 0.030903796952114485 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.03501438706296781, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.37373737373737376, "acc_stderr": 0.034468977386593325, "acc_norm": 0.37373737373737376, "acc_norm_stderr": 0.034468977386593325 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.3471502590673575, "acc_stderr": 0.03435696168361355, "acc_norm": 0.3471502590673575, "acc_norm_stderr": 0.03435696168361355 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.32051282051282054, "acc_stderr": 0.023661296393964273, "acc_norm": 0.32051282051282054, "acc_norm_stderr": 0.023661296393964273 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073835, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.026962424325073835 }, "harness|hendry