open-llm-leaderboard-old/details_dddsaty__Open_Ko_SOLAR_DPO_Merge_v0.1

该数据集是在Open LLM Leaderboard上对模型dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1进行评估时自动创建的。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的配置存储了所有运行的聚合结果，并用于计算和显示在Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在评估模型dddsaty/Open_Ko_SOLAR_DPO_Merge_v0.1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。每个运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。
• "train"分割始终指向最新的结果。
• 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_dddsaty__Open_Ko_SOLAR_DPO_Merge_v0.1", "harness_winogrande_5", split="train")

最新结果

以下是最新结果从运行2024-02-09T23:07:32.238009：

python { "all": { "acc": 0.5416265887130933, "acc_stderr": 0.03405336598874463, "acc_norm": 0.546122684766613, "acc_norm_stderr": 0.03477662766173176, "mc1": 0.25458996328029376, "mc1_stderr": 0.015250117079156494, "mc2": 0.4017204286168437, "mc2_stderr": 0.01413684738591521 }, "harness|arc:challenge|25": { "acc": 0.5238907849829352, "acc_stderr": 0.014594701798071654, "acc_norm": 0.5511945392491467, "acc_norm_stderr": 0.014534599585097664 }, "harness|hellaswag|10": { "acc": 0.5790679147580163, "acc_stderr": 0.0049269968301942305, "acc_norm": 0.7818163712407887, "acc_norm_stderr": 0.0041216867002386 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750575, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.040463368839782514, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.040463368839782514 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5735849056603773, "acc_stderr": 0.030437794342983045, "acc_norm": 0.5735849056603773, "acc_norm_stderr": 0.030437794342983045 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6319444444444444, "acc_stderr": 0.04032999053960719, "acc_norm": 0.6319444444444444, "acc_norm_stderr": 0.04032999053960719 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5202312138728323, "acc_stderr": 0.03809342081273956, "acc_norm": 0.5202312138728323, "acc_norm_stderr": 0.03809342081273956 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.044405219061793275, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.044405219061793275 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.48936170212765956, "acc_stderr": 0.03267862331014063, "acc_norm": 0.48936170212765956, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070435, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070435 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159788, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159788 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.040061680838488774, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.040061680838488774 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6225806451612903, "acc_stderr": 0.02757596072327824, "acc_norm": 0.6225806451612903, "acc_norm_stderr": 0.02757596072327824 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4236453201970443, "acc_stderr": 0.034767257476490364, "acc_norm": 0.4236453201970443, "acc_norm_stderr": 0.034767257476490364 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6606060606060606, "acc_stderr": 0.036974422050315967, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.036974422050315967 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7070707070707071, "acc_stderr": 0.03242497958178815, "acc_norm": 0.7070707070707071, "acc_norm_stderr": 0.03242497958178815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7098445595854922, "acc_stderr": 0.032752644677915166, "acc_norm": 0.7098445595854922, "acc_norm_stderr": 0.032752644677915166 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5, "acc_stderr": 0.02535100632816969, "acc_norm": 0.5, "acc_norm_stderr": 0.02535100632816969 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.0287420409039485, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.0287420409039485 }, "harness|hendrycksTest-high_school_microeconomics|5