open-llm-leaderboard-old/details_kyujinpy__PlatYi-34B-Llama-Q
收藏数据集概述
数据集简介
该数据集是在评估模型kyujinpy/PlatYi-34B-Llama-Q在Open LLM Leaderboard上的运行过程中自动创建的。
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。数据集是从1次运行中创建的，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。
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_kyujinpy__PlatYi-34B-Llama-Q", "harness_winogrande_5", split="train")
最新结果
以下是最新结果（注意可能有其他任务的结果，每个任务的最新结果可以在"results"和"latest"分割中找到）：
python { "all": { "acc": 0.78055182695593, "acc_stderr": 0.02737501256983463, "acc_norm": 0.7866450755467821, "acc_norm_stderr": 0.027870412250259477, "mc1": 0.38555691554467564, "mc1_stderr": 0.017038839010591673, "mc2": 0.5363792883186823, "mc2_stderr": 0.014951574037726555 }, "harness|arc:challenge|25": { "acc": 0.6220136518771331, "acc_stderr": 0.014169664520303096, "acc_norm": 0.6569965870307167, "acc_norm_stderr": 0.01387242322371816 }, "harness|hellaswag|10": { "acc": 0.6542521410077674, "acc_stderr": 0.004746394613384537, "acc_norm": 0.8522206731726748, "acc_norm_stderr": 0.00354155826377912 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7555555555555555, "acc_stderr": 0.03712537833614866, "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.025648341251693605, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.025648341251693605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.81, "acc_stderr": 0.03942772444036623, "acc_norm": 0.81, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8037735849056604, "acc_stderr": 0.024442388131100824, "acc_norm": 0.8037735849056604, "acc_norm_stderr": 0.024442388131100824 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9166666666666666, "acc_stderr": 0.023112508176051236, "acc_norm": 0.9166666666666666, "acc_norm_stderr": 0.023112508176051236 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.48, "acc_stderr": 0.05021167315686779, "acc_norm": 0.48, "acc_norm_stderr": 0.05021167315686779 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7283236994219653, "acc_stderr": 0.03391750322321659, "acc_norm": 0.7283236994219653, "acc_norm_stderr": 0.03391750322321659 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6078431372549019, "acc_stderr": 0.04858083574266345, "acc_norm": 0.6078431372549019, "acc_norm_stderr": 0.04858083574266345 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7957446808510639, "acc_stderr": 0.026355158413349417, "acc_norm": 0.7957446808510639, "acc_norm_stderr": 0.026355158413349417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6228070175438597, "acc_stderr": 0.04559522141958216, "acc_norm": 0.6228070175438597, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8137931034482758, "acc_stderr": 0.03243946159004616, "acc_norm": 0.8137931034482758, "acc_norm_stderr": 0.03243946159004616 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7619047619047619, "acc_stderr": 0.021935878081184763, "acc_norm": 0.7619047619047619, "acc_norm_stderr": 0.021935878081184763 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5952380952380952, "acc_stderr": 0.04390259265377562, "acc_norm": 0.5952380952380952, "acc_norm_stderr": 0.04390259265377562 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9290322580645162, "acc_stderr": 0.01460718907324613, "acc_norm": 0.9290322580645162, "acc_norm_stderr": 0.01460718907324613 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.7044334975369458, "acc_stderr": 0.032104944337514575, "acc_norm": 0.7044334975369458, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.84, "acc_stderr": 0.03684529491774708, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706463, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706463 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9242424242424242, "acc_stderr": 0.018852670234993107, "acc_norm": 0.9242424242424242, "acc_norm_stderr": 0.018852670234993107 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9792746113989638, "acc_stderr": 0.010281417011909036, "acc_norm": 0.9792746113989638, "acc_norm_stderr": 0.010281417011909036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8358974358974359, "acc_stderr": 0.01877843431342371, "acc_norm": 0.8358974358974359, "acc_norm_stderr": 0.01877843431342371 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4888888888888889, "acc_stderr": 0.030478009819615823, "acc_norm": 0.488888888888888
