open-llm-leaderboard-old/details_Eric111__NeuralBeagleOpenChat

该数据集是在Open LLM Leaderboard上对模型Eric111/NeuralBeagleOpenChat进行评估运行期间自动创建的。数据集由63个配置组成，每个配置对应一个被评估的任务。数据集是从一次运行中生成的，每次运行在每个配置中表示为特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。一个名为results的额外配置存储了运行的所有聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了一个如何使用Python中的datasets库加载运行细节的示例。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 Eric111/NeuralBeagleOpenChat 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。数据集从 1 次运行中创建，每次运行的详细结果可以在每个配置的特定分片中找到，分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。此外，一个名为 "results" 的配置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。

最新结果

以下是 2024-02-04T23:07:18.461587 运行的最新结果：

python { "all": { "acc": 0.6606606326765095, "acc_stderr": 0.03176172876813684, "acc_norm": 0.6604815290872796, "acc_norm_stderr": 0.03242278367605966, "mc1": 0.42962056303549573, "mc1_stderr": 0.017329234580409098, "mc2": 0.6091160375508784, "mc2_stderr": 0.015202500436432948 }, "harness|arc:challenge|25": { "acc": 0.6629692832764505, "acc_stderr": 0.013813476652902272, "acc_norm": 0.7030716723549488, "acc_norm_stderr": 0.013352025976725223 }, "harness|hellaswag|10": { "acc": 0.6699860585540729, "acc_stderr": 0.004692567655961763, "acc_norm": 0.8625771758613822, "acc_norm_stderr": 0.0034358953866922537 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6710526315789473, "acc_stderr": 0.03823428969926605, "acc_norm": 0.6710526315789473, "acc_norm_stderr": 0.03823428969926605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7169811320754716, "acc_stderr": 0.027724236492700918, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700918 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7916666666666666, "acc_stderr": 0.03396116205845333, "acc_norm": 0.7916666666666666, "acc_norm_stderr": 0.03396116205845333 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6936416184971098, "acc_stderr": 0.03514942551267438, "acc_norm": 0.6936416184971098, "acc_norm_stderr": 0.03514942551267438 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287533, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287533 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.03232146916224468, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370333, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370333 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.025446365634406783, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.023415293433568525, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.023415293433568525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.031922715695483016, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.031922715695483016 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586815, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586815 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033477, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033477 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6794871794871795, "acc_stderr": 0.02366129639396428, "acc_norm": 0.6794871794871795, "acc_norm_stderr": 0.02366129639396428 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083008, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.029116617606083008 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6890756302521008, "acc_stderr": 0.030066761582977934, "acc_norm": 0.6890756302521008, "acc_norm_stderr": 0