open-llm-leaderboard-old/details_NLUHOPOE__experiment2-cause
收藏数据集概述
数据集简介
该数据集是在评估模型 NLUHOPOE/experiment2-cause 在 Open LLM Leaderboard 上的运行过程中自动创建的。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 2 次运行结果组成，每次运行的详细结果可以在每个配置中找到，并以运行的时间戳命名。"train" 分割始终指向最新的结果。此外，还有一个名为 "results" 的配置，存储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
以下是加载特定运行详细结果的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_NLUHOPOE__experiment2-cause", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-02T01:23:01.648750 运行的最新结果： python { "all": { "acc": 0.6187092967805649, "acc_stderr": 0.03277112039995135, "acc_norm": 0.6247066510159702, "acc_norm_stderr": 0.03344268306035278, "mc1": 0.3268053855569155, "mc1_stderr": 0.016419874731135025, "mc2": 0.4713263218122602, "mc2_stderr": 0.01458246045981096 }, "harness|arc:challenge|25": { "acc": 0.5554607508532423, "acc_stderr": 0.014521226405627077, "acc_norm": 0.6040955631399317, "acc_norm_stderr": 0.014291228393536588 }, "harness|hellaswag|10": { "acc": 0.6210914160525791, "acc_stderr": 0.004841238763529372, "acc_norm": 0.8276239792869946, "acc_norm_stderr": 0.003769350079195885 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316092, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316092 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7018867924528301, "acc_stderr": 0.028152837942493864, "acc_norm": 0.7018867924528301, "acc_norm_stderr": 0.028152837942493864 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5895953757225434, "acc_stderr": 0.03750757044895537, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.548936170212766, "acc_stderr": 0.032529096196131965, "acc_norm": 0.548936170212766, "acc_norm_stderr": 0.032529096196131965 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482758, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.025043757318520196, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.025043757318520196 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7258064516129032, "acc_stderr": 0.025378139970885196, "acc_norm": 0.7258064516129032, "acc_norm_stderr": 0.025378139970885196 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885417, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885417 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586818, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586818 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.844559585492228, "acc_stderr": 0.02614848346915333, "acc_norm": 0.844559585492228, "acc_norm_stderr": 0.02614848346915333 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6282051282051282, "acc_stderr": 0.024503472557110932, "acc_norm": 0.6282051282051282, "acc_norm_stderr": 0.024503472557110932 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253255, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.02882
