open-llm-leaderboard-old/details_crumb__nano-mistral

该数据集是在Open LLM Leaderboard上对模型crumb/nano-mistral进行评估运行时自动创建的。数据集由63个配置组成，每个配置对应一个评估任务。数据集由1次运行创建，每次运行作为每个配置中的特定分割，分割名称使用运行的时间戳。train分割始终指向最新结果。此外，还有一个名为results的配置，存储了所有运行的聚合结果，用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。

原始信息汇总

数据集概述

数据集描述

该数据集是在对模型 crumb/nano-mistral 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 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，每个运行可以在每个配置中作为一个特定的分割找到，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。

最新结果

最新结果来自 2024-03-10T00:27:55.291023 运行，包含多个任务的评估结果，具体结果如下：

python { "all": { "acc": 0.2511203777273379, "acc_stderr": 0.03056453888033514, "acc_norm": 0.2515472364859563, "acc_norm_stderr": 0.03137819323372588, "mc1": 0.2607099143206854, "mc1_stderr": 0.015368841620766368, "mc2": 0.4741805949532385, "mc2_stderr": 0.015622084311020428 }, "harness|arc:challenge|25": { "acc": 0.17747440273037543, "acc_stderr": 0.01116513876964396, "acc_norm": 0.2167235494880546, "acc_norm_stderr": 0.01204015671348119 }, "harness|hellaswag|10": { "acc": 0.27743477394941246, "acc_stderr": 0.004468178273665653, "acc_norm": 0.28520215096594304, "acc_norm_stderr": 0.004505879084606852 }, "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": 0.2518518518518518, "acc_stderr": 0.03749850709174022, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.03749850709174022 }, "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": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2339622641509434, "acc_stderr": 0.02605529690115292, "acc_norm": 0.2339622641509434, "acc_norm_stderr": 0.02605529690115292 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.030631145539198813, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.030631145539198813 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2549019607843137, "acc_stderr": 0.04336432707993177, "acc_norm": 0.2549019607843137, "acc_norm_stderr": 0.04336432707993177 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.2, "acc_stderr": 0.04020151261036843, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.02880998985410297, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.02880998985410297 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.040493392977481404, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.040493392977481404 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.27586206896551724, "acc_stderr": 0.037245636197746325, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.037245636197746325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113942, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113942 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.18253968253968253, "acc_stderr": 0.03455071019102146, "acc_norm": 0.18253968253968253, "acc_norm_stderr": 0.03455071019102146 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.15, "acc_stderr": 0.035887028128263686, "acc_norm": 0.15, "acc_norm_stderr": 0.035887028128263686 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3032258064516129, "acc_stderr": 0.02614868593067175, "acc_norm": 0.3032258064516129, "acc_norm_stderr": 0.02614868593067175 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.270935960591133, "acc_stderr": 0.031270907132976984, "acc_norm": 0.270935960591133, "acc_norm_stderr": 0.031270907132976984 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.032568666616811015, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365897, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.030276909945178253, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.030276909945178253 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.25384615384615383, "acc_stderr": 0.022066054378726257, "acc_norm": 0.25384615384615383, "acc_norm_stderr": 0.022066054378726257 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073828, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.026962424325073828 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.23949579831932774, "acc_stderr": 0.027722065493361273, "acc_norm": 0.2394