open-llm-leaderboard-old/details_fzzhang__mistralv1_gsm8k_merged_s

该数据集是在模型fzzhang/mistralv1_gsm8k_merged_s在Open LLM Leaderboard上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1次运行中创建的，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。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在模型fzzhang/mistralv1_gsm8k_merged_s的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2024-02-16T22:54:23.549032运行的最新结果：

python { "all": { "acc": 0.6168865618276048, "acc_stderr": 0.03272942181052946, "acc_norm": 0.620454228546075, "acc_norm_stderr": 0.03338469630654732, "mc1": 0.2729498164014688, "mc1_stderr": 0.015594753632006526, "mc2": 0.42426145726798214, "mc2_stderr": 0.014425554324623623 }, "harness|arc:challenge|25": { "acc": 0.5827645051194539, "acc_stderr": 0.014409825518403084, "acc_norm": 0.6203071672354948, "acc_norm_stderr": 0.014182119866974872 }, "harness|hellaswag|10": { "acc": 0.6467835092611034, "acc_stderr": 0.004769924131304649, "acc_norm": 0.8394742083250348, "acc_norm_stderr": 0.0036634275361781595 }, "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": 0.5555555555555556, "acc_stderr": 0.04292596718256981, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04292596718256981 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.039105257528497236, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.039105257528497236 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7083333333333334, "acc_stderr": 0.038009680605548594, "acc_norm": 0.7083333333333334, "acc_norm_stderr": 0.038009680605548594 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.03643037168958548, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.03643037168958548 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.04951218252396262, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396262 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4851063829787234, "acc_stderr": 0.032671518489247764, "acc_norm": 0.4851063829787234, "acc_norm_stderr": 0.032671518489247764 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.046570472605949625, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.046570472605949625 }, "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": 0.3783068783068783, "acc_stderr": 0.02497695405315524, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.02497695405315524 }, "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": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7516129032258064, "acc_stderr": 0.024580028921481003, "acc_norm": 0.7516129032258064, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494562, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494562 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758733, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758733 }, "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": 0.3333333333333333, "acc_stderr": 0.028742040903948485, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948485 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6260