open-llm-leaderboard-old/details_Zangs3011__gpt2_137m_DolphinCoder

该数据集是在模型Zangs3011/gpt2_137m_DolphinCoder的评估运行中自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集是从1次运行中创建的，每次运行都可以在特定配置中找到，分割使用运行的时间戳命名。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

数据集简介

该数据集是在评估模型Zangs3011/gpt2_137m_DolphinCoder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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Zangs3011__gpt2_137m_DolphinCoder", "harness_winogrande_5", split="train")

最新结果

以下是最新结果：

python { "all": { "acc": 0.2541058154915133, "acc_stderr": 0.030552087768393632, "acc_norm": 0.2544491269494238, "acc_norm_stderr": 0.03131084218129606, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023496, "mc2": 0.41575126598869544, "mc2_stderr": 0.015079894627974334 }, "harness|arc:challenge|25": { "acc": 0.19795221843003413, "acc_stderr": 0.011643990971573395, "acc_norm": 0.21843003412969283, "acc_norm_stderr": 0.012074291605700983 }, "harness|hellaswag|10": { "acc": 0.29117705636327423, "acc_stderr": 0.00453376468621199, "acc_norm": 0.3134833698466441, "acc_norm_stderr": 0.004629608863272312 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2814814814814815, "acc_stderr": 0.038850042458002554, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.038850042458002554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.19, "acc_stderr": 0.03942772444036623, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22641509433962265, "acc_stderr": 0.025757559893106737, "acc_norm": 0.22641509433962265, "acc_norm_stderr": 0.025757559893106737 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2152777777777778, "acc_stderr": 0.034370793441061344, "acc_norm": 0.2152777777777778, "acc_norm_stderr": 0.034370793441061344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909281, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932269, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932269 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24855491329479767, "acc_stderr": 0.03295304696818318, "acc_norm": 0.24855491329479767, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.043364327079931785, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.043364327079931785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.19, "acc_stderr": 0.03942772444036622, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036622 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.03999423879281336, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.03999423879281336 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3103448275862069, "acc_stderr": 0.038552896163789485, "acc_norm": 0.3103448275862069, "acc_norm_stderr": 0.038552896163789485 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.24074074074074073, "acc_stderr": 0.022019080012217893, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.022019080012217893 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1349206349206349, "acc_stderr": 0.030557101589417508, "acc_norm": 0.1349206349206349, "acc_norm_stderr": 0.030557101589417508 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2129032258064516, "acc_stderr": 0.023287665127268552, "acc_norm": 0.2129032258064516, "acc_norm_stderr": 0.023287665127268552 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21674876847290642, "acc_stderr": 0.028990331252516235, "acc_norm": 0.21674876847290642, "acc_norm_stderr": 0.028990331252516235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21212121212121213, "acc_stderr": 0.03192271569548299, "acc_norm": 0.21212121212121213, "acc_norm_stderr": 0.03192271569548299 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.35353535353535354, "acc_stderr": 0.03406086723547153, "acc_norm": 0.35353535353535354, "acc_norm_stderr": 0.03406086723547153 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.36787564766839376, "acc_stderr": 0.03480175668466036, "acc_norm": 0.36787564766839376, "acc_norm_stderr": 0.03480175668466036 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2230769230769231, "acc_stderr": 0.02110773012724399, "acc_norm": 0.2230769230769231, "acc_norm_stderr": 0.02110773012724399 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2518518518518518, "acc_stderr": 0.026466117538959916, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.026466117538959916 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc":