open-llm-leaderboard-old/details_jisukim8873__mistral-7B-alpaca-1-epoch

该数据集是在评估模型jisukim8873/mistral-7B-alpaca-1-epoch运行期间自动创建的，用于Open LLM排行榜。数据集包含63个配置，每个配置对应一个评估任务。每个配置包含特定的时间戳命名的分割，其中train分割始终指向最新结果。额外的results配置存储了运行的所有聚合结果，用于在排行榜上计算和显示聚合指标。数据集结构允许使用HuggingFace的数据集库加载特定运行的详细信息。

原始信息汇总

数据集概述

数据集摘要

该数据集是在评估模型 jisukim8873/mistral-7B-alpaca-1-epoch 在 Open LLM Leaderboard 上的运行过程中自动创建的。

数据集组成

• 该数据集包含 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 2024-04-02T15:14:07.599326 运行的最新结果：

python { "all": { "acc": 0.6278105844794349, "acc_stderr": 0.03263571334344304, "acc_norm": 0.6340078517295734, "acc_norm_stderr": 0.03330022649164498, "mc1": 0.30599755201958384, "mc1_stderr": 0.016132229728155045, "mc2": 0.43345276846678576, "mc2_stderr": 0.01456863855851223 }, "harness|arc:challenge|25": { "acc": 0.5776450511945392, "acc_stderr": 0.014434138713379977, "acc_norm": 0.6177474402730375, "acc_norm_stderr": 0.014200454049979275 }, "harness|hellaswag|10": { "acc": 0.6289583748257319, "acc_stderr": 0.004820962855749739, "acc_norm": 0.8266281617207728, "acc_norm_stderr": 0.0037779472688574496 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.038947344870133176, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.038947344870133176 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "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": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.653179190751445, "acc_stderr": 0.036291466701596636, "acc_norm": 0.653179190751445, "acc_norm_stderr": 0.036291466701596636 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726366, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726366 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.04685473041907789, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.04685473041907789 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482757, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.025305906241590632, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.025305906241590632 }, "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": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895518, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895518 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.028335609732463362, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.028335609732463362 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.02649905770139746, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.02649905770139746 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.023991500500313036, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.023991500500313036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.028972648884844267, "acc_norm": 0.34444444444444444, "acc_norm_stderr": 0.028972648884844267 }, "harness|hendrycksTest-high_school_microeconomics|5": {