open-llm-leaderboard-old/details_ab24g21__LaterLlamaV2
收藏数据集概述
数据集来源
该数据集是在评估模型 ab24g21/LaterLlamaV2 在 Open LLM Leaderboard 上的自动创建的。
数据集组成
数据集由 63 个配置组成，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。
结果配置
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。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ab24g21__LaterLlamaV2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-29T19:09:56.465728 运行的最新结果：
python { "all": { "acc": 0.5461869266998542, "acc_stderr": 0.033788120399471086, "acc_norm": 0.5507018751608478, "acc_norm_stderr": 0.034496936259557756, "mc1": 0.2839657282741738, "mc1_stderr": 0.01578537085839672, "mc2": 0.4414865313489548, "mc2_stderr": 0.015331891416062246 }, "harness|arc:challenge|25": { "acc": 0.5511945392491467, "acc_stderr": 0.014534599585097667, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.014370358632472435 }, "harness|hellaswag|10": { "acc": 0.6230830511850229, "acc_stderr": 0.004836234143655406, "acc_norm": 0.8181637124078869, "acc_norm_stderr": 0.0038492126228151734 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526066, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526066 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5037037037037037, "acc_stderr": 0.04319223625811331, "acc_norm": 0.5037037037037037, "acc_norm_stderr": 0.04319223625811331 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5460526315789473, "acc_stderr": 0.04051646342874142, "acc_norm": 0.5460526315789473, "acc_norm_stderr": 0.04051646342874142 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.569811320754717, "acc_stderr": 0.030471445867183238, "acc_norm": 0.569811320754717, "acc_norm_stderr": 0.030471445867183238 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5972222222222222, "acc_stderr": 0.04101405519842426, "acc_norm": 0.5972222222222222, "acc_norm_stderr": 0.04101405519842426 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "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": 0.48554913294797686, "acc_stderr": 0.03810871630454764, "acc_norm": 0.48554913294797686, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.04576665403207763, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.04576665403207763 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "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": 0.34656084656084657, "acc_stderr": 0.024508777521028424, "acc_norm": 0.34656084656084657, "acc_norm_stderr": 0.024508777521028424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.30952380952380953, "acc_norm_stderr": 0.04134913018303316 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6516129032258065, "acc_stderr": 0.027104826328100944, "acc_norm": 0.6516129032258065, "acc_norm_stderr": 0.027104826328100944 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6787878787878788, "acc_stderr": 0.036462049632538115, "acc_norm": 0.6787878787878788, "acc_norm_stderr": 0.036462049632538115 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6919191919191919, "acc_stderr": 0.032894773300986155, "acc_norm": 0.6919191919191919, "acc_norm_stderr": 0.032894773300986155 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.029778663037752954, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.029778663037752954 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.49230769230769234, "acc_stderr": 0.025348006031534785, "acc_norm": 0.49230769230769234, "acc_norm_stderr": 0.025348006031534785 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340496, "acc_norm": 0.2851851851851852,
