open-llm-leaderboard-old/details_Stopwolf__Cerberus-7B-slerp

该数据集是在评估模型Stopwolf/Cerberus-7B-slerp时自动创建的，主要用于在Open LLM Leaderboard上展示评估结果。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一个特定的分割存储，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，用于计算和展示在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 Stopwolf/Cerberus-7B-slerp 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 2024-02-05T09:08:12.484477 运行的最新结果：

python { "all": { "acc": 0.629678937070562, "acc_stderr": 0.03233409511653798, "acc_norm": 0.6376621349483272, "acc_norm_stderr": 0.0330388306090536, "mc1": 0.44920440636474906, "mc1_stderr": 0.017412941986115302, "mc2": 0.6135075599156891, "mc2_stderr": 0.01558423055084616 }, "harness|arc:challenge|25": { "acc": 0.6723549488054608, "acc_stderr": 0.01371584794071934, "acc_norm": 0.6953924914675768, "acc_norm_stderr": 0.013449522109932487 }, "harness|hellaswag|10": { "acc": 0.6920932085241984, "acc_stderr": 0.004606843344517468, "acc_norm": 0.8733320055765784, "acc_norm_stderr": 0.0033192094001351165 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6776315789473685, "acc_stderr": 0.038035102483515854, "acc_norm": 0.6776315789473685, "acc_norm_stderr": 0.038035102483515854 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.02825420034443866, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.02825420034443866 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6416184971098265, "acc_stderr": 0.036563436533531585, "acc_norm": 0.6416184971098265, "acc_norm_stderr": 0.036563436533531585 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.04784060704105653, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.04784060704105653 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.046970851366478626, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.046970851366478626 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086924, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086924 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7774193548387097, "acc_stderr": 0.02366421667164251, "acc_norm": 0.7774193548387097, "acc_norm_stderr": 0.02366421667164251 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.029376616484945627, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.029376616484945627 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.02293514405391943, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.02293514405391943 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6230769230769231, "acc_stderr": 0.024570975364225995, "acc_norm": 0.6230769230769231, "acc_norm_stderr": 0.024570975364225995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32222222222222224, "acc_stderr": 0.028493465091028593, "acc_norm": 0.32222222222222224, "acc_norm_stderr": 0.028493465091028593 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6176470588235294, "acc_stderr": 0.031566630992154156, "acc_norm":