open-llm-leaderboard/details_Qwen__Qwen2-72B

该数据集是在Open LLM Leaderboard上对Qwen/Qwen2-72B模型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。此外，还有一个results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`函数加载数据集的示例。

原始信息汇总

数据集概述

数据集名称

Evaluation run of Qwen/Qwen2-72B

数据集摘要

该数据集是在模型 Qwen/Qwen2-72B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

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，每次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

以下是 2024-05-30T19:20:17.942751 运行 的最新结果：

python { "all": { "acc": 0.8326744621410869, "acc_stderr": 0.02515669535436435, "acc_norm": 0.8359507487155015, "acc_norm_stderr": 0.025643417234058778, "mc1": 0.3733170134638923, "mc1_stderr": 0.016932370557570627, "mc2": 0.5473731276983239, "mc2_stderr": 0.014519749581903284 }, "harness|arc:challenge|25": { "acc": 0.658703071672355, "acc_stderr": 0.013855831287497726, "acc_norm": 0.6877133105802048, "acc_norm_stderr": 0.013542598541688065 }, "harness|hellaswag|10": { "acc": 0.6763592909778928, "acc_stderr": 0.004669085411342196, "acc_norm": 0.8727345150368453, "acc_norm_stderr": 0.003325890225529866 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.8, "acc_stderr": 0.03455473702325438, "acc_norm": 0.8, "acc_norm_stderr": 0.03455473702325438 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.9210526315789473, "acc_stderr": 0.021944342818247937, "acc_norm": 0.9210526315789473, "acc_norm_stderr": 0.021944342818247937 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.04020151261036844, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036844 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8716981132075472, "acc_stderr": 0.020582475687991857, "acc_norm": 0.8716981132075472, "acc_norm_stderr": 0.020582475687991857 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.9305555555555556, "acc_stderr": 0.021257974822832038, "acc_norm": 0.9305555555555556, "acc_norm_stderr": 0.021257974822832038 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.838150289017341, "acc_stderr": 0.028083594279575762, "acc_norm": 0.838150289017341, "acc_norm_stderr": 0.028083594279575762 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.6568627450980392, "acc_stderr": 0.04724007352383889, "acc_norm": 0.6568627450980392, "acc_norm_stderr": 0.04724007352383889 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.036845294917747094, "acc_norm": 0.84, "acc_norm_stderr": 0.036845294917747094 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.8936170212765957, "acc_stderr": 0.02015597730704988, "acc_norm": 0.8936170212765957, "acc_norm_stderr": 0.02015597730704988 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.7368421052631579, "acc_stderr": 0.041424397194893686, "acc_norm": 0.7368421052631579, "acc_norm_stderr": 0.041424397194893686 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.8206896551724138, "acc_stderr": 0.031967664333731854, "acc_norm": 0.8206896551724138, "acc_norm_stderr": 0.031967664333731854 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.8862433862433863, "acc_stderr": 0.0163528764804948, "acc_norm": 0.8862433862433863, "acc_norm_stderr": 0.0163528764804948 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.7380952380952381, "acc_stderr": 0.03932537680392871, "acc_norm": 0.7380952380952381, "acc_norm_stderr": 0.03932537680392871 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9354838709677419, "acc_stderr": 0.013975683705589406, "acc_norm": 0.9354838709677419, "acc_norm_stderr": 0.013975683705589406 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.7783251231527094, "acc_stderr": 0.0292255758924896, "acc_norm": 0.7783251231527094, "acc_norm_stderr": 0.0292255758924896 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.91, "acc_stderr": 0.028762349126466115, "acc_norm": 0.91, "acc_norm_stderr": 0.028762349126466115 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8848484848484849, "acc_stderr": 0.024925699798115347, "acc_norm": 0.8848484848484849, "acc_norm_stderr": 0.024925699798115347 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9393939393939394, "acc_stderr": 0.01699999492742161, "acc_norm": 0.9393939393939394, "acc_norm_stderr": 0.01699999492742161 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9896373056994818, "acc_stderr": 0.007308424386792192, "acc_norm": 0.9896373056994818, "acc_norm_stderr": 0.007308424386792192 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.882051282051282, "acc_stderr": 0.016353801778303412, "acc_norm": 0.882051282051282, "acc_norm_stderr": 0.016353801778303412 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.6851851851851852, "acc_stderr": 0.028317533496066475, "acc_norm": 0.6851851851851852, "acc_norm_stderr": 0.028317533496066475 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.9369747899159664, "acc_stderr": 0.0157850852236