open-llm-leaderboard-old/details_Gryphe__MythoMist-7b
收藏数据集概述
数据集简介
该数据集是在评估模型 Gryphe/MythoMist-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。
数据集结构
数据集由 1 次运行创建，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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Gryphe__MythoMist-7b_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-23T18:33:43.562121 运行的最新结果：
python { "all": { "acc": 0.6193933424443757, "acc_stderr": 0.03253049842540975, "acc_norm": 0.6273757812096611, "acc_norm_stderr": 0.03322659183767027, "mc1": 0.43818849449204406, "mc1_stderr": 0.017369236164404445, "mc2": 0.5997836138576584, "mc2_stderr": 0.015379030818687125, "em": 0.22902684563758388, "em_stderr": 0.0043033084382756255, "f1": 0.37819945469799016, "f1_stderr": 0.004228456430289263 }, "harness|arc:challenge|25": { "acc": 0.6348122866894198, "acc_stderr": 0.014070265519268802, "acc_norm": 0.658703071672355, "acc_norm_stderr": 0.013855831287497728 }, "harness|hellaswag|10": { "acc": 0.6441943835889266, "acc_stderr": 0.0047777825848177875, "acc_norm": 0.8354909380601474, "acc_norm_stderr": 0.003699791934754364 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.03842498559395268, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.03842498559395268 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.04793724854411019, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411019 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.03692820767264866, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.03692820767264866 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.044084400227680794, "acc_norm": 0.74, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5319148936170213, "acc_stderr": 0.03261936918467381, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467381 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36772486772486773, "acc_stderr": 0.02483383982556242, "acc_norm": 0.36772486772486773, "acc_norm_stderr": 0.02483383982556242 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.0442626668137991, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.0442626668137991 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7645161290322581, "acc_stderr": 0.024137632429337717, "acc_norm": 0.7645161290322581, "acc_norm_stderr": 0.024137632429337717 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "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": 0.7676767676767676, "acc_stderr": 0.03008862949021749, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.03008862949021749 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033446, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033446 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6128205128205129, "acc_stderr": 0.024697216930878937, "acc_norm": 0.6128205128205129, "acc_norm_stderr": 0.024697216930878937 }, "harness|hendry
