open-llm-leaderboard-old/details_NLUHOPOE__test-case-6

该数据集是在Open LLM Leaderboard上对模型NLUHOPOE/test-case-6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。它包含1次运行的结果，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分割始终指向最新结果。一个名为results的额外配置存储了所有运行的聚合结果，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

该数据集是在对模型 NLUHOPOE/test-case-6 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。
• 额外的 "results" 配置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

以下是 2024-03-01T01:53:21.380144 运行的最新结果：

python { "all": { "acc": 0.5803688532480622, "acc_stderr": 0.03360323649201099, "acc_norm": 0.5854412322412027, "acc_norm_stderr": 0.03430537577014263, "mc1": 0.3317013463892289, "mc1_stderr": 0.016482148810241473, "mc2": 0.49443365843236614, "mc2_stderr": 0.01529725057307427 }, "harness|arc:challenge|25": { "acc": 0.523037542662116, "acc_stderr": 0.01459587320535827, "acc_norm": 0.5733788395904437, "acc_norm_stderr": 0.014453185592920293 }, "harness|hellaswag|10": { "acc": 0.5995817566221868, "acc_stderr": 0.004889817489739686, "acc_norm": 0.7885879306910973, "acc_norm_stderr": 0.004074754687134535 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.045126085985421296, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421296 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.042039210401562783, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.03894734487013316, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.03894734487013316 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6528301886792452, "acc_stderr": 0.029300101705549655, "acc_norm": 0.6528301886792452, "acc_norm_stderr": 0.029300101705549655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.5953757225433526, "acc_stderr": 0.03742461193887248, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.048108401480826346, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.048108401480826346 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.67, "acc_stderr": 0.047258156262526066, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526066 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4765957446808511, "acc_stderr": 0.03265019475033582, "acc_norm": 0.4765957446808511, "acc_norm_stderr": 0.03265019475033582 }, "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": 0.5586206896551724, "acc_stderr": 0.04137931034482758, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482758 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36772486772486773, "acc_stderr": 0.024833839825562424, "acc_norm": 0.36772486772486773, "acc_norm_stderr": 0.024833839825562424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377562, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377562 }, "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": 0.027575960723278246, "acc_norm": 0.6225806451612903, "acc_norm_stderr": 0.027575960723278246 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.42857142857142855, "acc_stderr": 0.034819048444388045, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.034819048444388045 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.030313710538198906, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.030313710538198906 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7979274611398963, "acc_stderr": 0.028979089794296732, "acc_norm": 0.7979274611398963, "acc_norm_stderr": 0.028979089794296732 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5846153846153846, "acc_stderr": 0.02498535492310234, "acc_norm": 0.5846153846153846, "acc_norm_stderr": 0.02498535492310234 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.02882088466625326, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.02882088466625326 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6386554621848739, "acc_stderr":