open-llm-leaderboard-old/details_maywell__kiqu-70b
收藏数据集概述
数据集来源
该数据集是在评估模型 maywell/kiqu-70b 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拆分，拆分名称使用运行的时间戳。"train" 拆分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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_maywell__kiqu-70b", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-02-18T20:08:41.581583 的运行：
python { "all": { "acc": 0.7477501453776264, "acc_stderr": 0.02896486498215866, "acc_norm": 0.7510302775108164, "acc_norm_stderr": 0.029526287642327367, "mc1": 0.46511627906976744, "mc1_stderr": 0.017460849975873965, "mc2": 0.6348399492810686, "mc2_stderr": 0.014841108878766373 }, "harness|arc:challenge|25": { "acc": 0.6749146757679181, "acc_stderr": 0.01368814730972912, "acc_norm": 0.7209897610921502, "acc_norm_stderr": 0.01310678488360134 }, "harness|hellaswag|10": { "acc": 0.6943835889265086, "acc_stderr": 0.004597265399568739, "acc_norm": 0.8794064927305317, "acc_norm_stderr": 0.0032498873947065057 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8355263157894737, "acc_stderr": 0.030167533468632726, "acc_norm": 0.8355263157894737, "acc_norm_stderr": 0.030167533468632726 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.04020151261036844, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036844 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.024079995130062228, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.024079995130062228 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8819444444444444, "acc_stderr": 0.026983346503309347, "acc_norm": 0.8819444444444444, "acc_norm_stderr": 0.026983346503309347 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7630057803468208, "acc_stderr": 0.032424147574830975, "acc_norm": 0.7630057803468208, "acc_norm_stderr": 0.032424147574830975 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5098039215686274, "acc_stderr": 0.04974229460422817, "acc_norm": 0.5098039215686274, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.03942772444036624, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7446808510638298, "acc_stderr": 0.028504856470514258, "acc_norm": 0.7446808510638298, "acc_norm_stderr": 0.028504856470514258 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5614035087719298, "acc_stderr": 0.04668000738510455, "acc_norm": 0.5614035087719298, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.03724563619774632, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.03724563619774632 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5370370370370371, "acc_stderr": 0.025680564640056882, "acc_norm": 0.5370370370370371, "acc_norm_stderr": 0.025680564640056882 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04444444444444449, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8741935483870967, "acc_stderr": 0.018865834288030008, "acc_norm": 0.8741935483870967, "acc_norm_stderr": 0.018865834288030008 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.625615763546798, "acc_stderr": 0.03405155380561952, "acc_norm": 0.625615763546798, "acc_norm_stderr": 0.03405155380561952 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8363636363636363, "acc_stderr": 0.02888787239548795, "acc_norm": 0.8363636363636363, "acc_norm_stderr": 0.02888787239548795 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9141414141414141, "acc_stderr": 0.01996022556317289, "acc_norm": 0.9141414141414141, "acc_norm_stderr": 0.01996022556317289 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9430051813471503, "acc_stderr": 0.01673108529360756, "acc_norm": 0.9430051813471503, "acc_norm_stderr": 0.01673108529360756 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7769230769230769, "acc_stderr": 0.02110773012724401, "acc_norm": 0.7769230769230769, "acc_norm_stderr": 0.02110773012724401 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.029381620726465073, "acc_norm": 0.36666666666666664, "acc_norm_stderr": 0.029381620726465073 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8361344537815126, "acc_stderr": 0.024
