open-llm-leaderboard-old/details_maldv__hyperdrive-7b-alpha

该数据集是在模型maldv/hyperdrive-7b-alpha的评估运行期间自动创建的，用于Open LLM Leaderboard的评估。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次运行生成，每次运行的结果作为特定的分割存储在配置中，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。

原始信息汇总

数据集概述

该数据集是在对模型 maldv/hyperdrive-7b-alpha 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 2024-04-16T01:28:11.438987 运行的最新结果：

python { "all": { "acc": 0.548469635515316, "acc_stderr": 0.033987335538742613, "acc_norm": 0.5553182749943731, "acc_norm_stderr": 0.03472009522374453, "mc1": 0.2998776009791922, "mc1_stderr": 0.01604035296671363, "mc2": 0.4468188470980979, "mc2_stderr": 0.01537365436297537 }, "harness|arc:challenge|25": { "acc": 0.5307167235494881, "acc_stderr": 0.014583792546304037, "acc_norm": 0.5631399317406144, "acc_norm_stderr": 0.014494421584256519 }, "harness|hellaswag|10": { "acc": 0.5942043417645887, "acc_stderr": 0.004900417982582052, "acc_norm": 0.7925712009559849, "acc_norm_stderr": 0.004046366223009965 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5333333333333333, "acc_stderr": 0.043097329010363554, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5526315789473685, "acc_stderr": 0.04046336883978251, "acc_norm": 0.5526315789473685, "acc_norm_stderr": 0.04046336883978251 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5735849056603773, "acc_stderr": 0.030437794342983045, "acc_norm": 0.5735849056603773, "acc_norm_stderr": 0.030437794342983045 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5433526011560693, "acc_stderr": 0.03798106566014498, "acc_norm": 0.5433526011560693, "acc_norm_stderr": 0.03798106566014498 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006718, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006718 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.46382978723404256, "acc_stderr": 0.032600385118357715, "acc_norm": 0.46382978723404256, "acc_norm_stderr": 0.032600385118357715 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939391, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939391 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5310344827586206, "acc_stderr": 0.04158632762097828, "acc_norm": 0.5310344827586206, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.373015873015873, "acc_stderr": 0.02490699045899257, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.02490699045899257 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6290322580645161, "acc_stderr": 0.027480541887953586, "acc_norm": 0.6290322580645161, "acc_norm_stderr": 0.027480541887953586 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4187192118226601, "acc_stderr": 0.03471192860518468, "acc_norm": 0.4187192118226601, "acc_norm_stderr": 0.03471192860518468 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6909090909090909, "acc_stderr": 0.036085410115739666, "acc_norm": 0.6909090909090909, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6616161616161617, "acc_stderr": 0.03371124142626303, "acc_norm": 0.6616161616161617, "acc_norm_stderr": 0.03371124142626303 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.772020725388601, "acc_stderr": 0.030276909945178256, "acc_norm": 0.772020725388601, "acc_norm_stderr": 0.030276909945178256 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5256410256410257, "acc_stderr": 0.025317649726448666, "acc_norm": 0.5256410256410257, "acc_norm_stderr": 0.025317649726448666 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945266, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945266 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5630252100840336, "acc_stderr": 0.032