open-llm-leaderboard-old/details_kevin009__flyingllama-v2
收藏数据集概述
数据集简介
该数据集是在评估模型 kevin009/flyingllama-v2 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 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。
额外配置
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_kevin009__flyingllama-v2", "harness_winogrande_5", split="train")
最新结果
这些是最新结果（来自 2024-02-04T09:40:33.484186 运行）的摘要：
python { "all": { "acc": 0.26355828648354096, "acc_stderr": 0.030989295716946252, "acc_norm": 0.26547327723680664, "acc_norm_stderr": 0.031814473208964, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.41299297017962017, "mc2_stderr": 0.014938905945440792 }, "harness|arc:challenge|25": { "acc": 0.2158703071672355, "acc_stderr": 0.012022975360030672, "acc_norm": 0.24744027303754265, "acc_norm_stderr": 0.01261035266329267 }, "harness|hellaswag|10": { "acc": 0.32732523401712804, "acc_stderr": 0.004682780790508346, "acc_norm": 0.3843855805616411, "acc_norm_stderr": 0.004854555294017559 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.26666666666666666, "acc_stderr": 0.03820169914517904, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.03820169914517904 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19736842105263158, "acc_stderr": 0.03238981601699397, "acc_norm": 0.19736842105263158, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.24150943396226415, "acc_stderr": 0.02634148037111836, "acc_norm": 0.24150943396226415, "acc_norm_stderr": 0.02634148037111836 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.23699421965317918, "acc_stderr": 0.03242414757483099, "acc_norm": 0.23699421965317918, "acc_norm_stderr": 0.03242414757483099 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006717, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006717 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.22, "acc_stderr": 0.0416333199893227, "acc_norm": 0.22, "acc_norm_stderr": 0.0416333199893227 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.19574468085106383, "acc_stderr": 0.025937853139977148, "acc_norm": 0.19574468085106383, "acc_norm_stderr": 0.025937853139977148 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813344, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813344 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.036001056927277716, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.036001056927277716 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24867724867724866, "acc_stderr": 0.022261817692400175, "acc_norm": 0.24867724867724866, "acc_norm_stderr": 0.022261817692400175 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523811, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523811 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2903225806451613, "acc_stderr": 0.025822106119415888, "acc_norm": 0.2903225806451613, "acc_norm_stderr": 0.025822106119415888 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.27586206896551724, "acc_stderr": 0.03144712581678241, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.03144712581678241 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.23030303030303031, "acc_stderr": 0.03287666758603488, "acc_norm": 0.23030303030303031, "acc_norm_stderr": 0.03287666758603488 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3484848484848485, "acc_stderr": 0.033948539651564025, "acc_norm": 0.3484848484848485, "acc_norm_stderr": 0.033948539651564025 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.33678756476683935, "acc_stderr": 0.034107802518361825, "acc_norm": 0.33678756476683935, "acc_norm_stderr": 0.034107802518361825 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.33589743589743587, "acc_stderr": 0.023946724741563976, "acc_norm": 0.33589743589743587, "acc_norm_stderr": 0.023946724741563976 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.027080372815145668, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.027080372815145668 }, "harness|hendrycksTest-high_school_microeconomics|5
