open-llm-leaderboard-old/details_Gille__StrangeMerges_37-7B-dare_ties

该数据集是自动创建的，用于评估模型Gille/StrangeMerges_37-7B-dare_ties在Open LLM Leaderboard上的表现。数据集包含63个配置，每个配置对应一个评估任务。数据集由一个运行创建，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。此外，还有一个名为"results"的配置，存储所有运行的聚合结果，用于计算和显示Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 Gille/StrangeMerges_37-7B-dare_ties 进行评估运行期间自动创建的。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，每次运行的详细信息可以在每个配置中找到，以运行的时间戳命名的特定分割形式存储。"train" 分割始终指向最新的结果。此外，一个名为 "results" 的额外配置存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

最新结果

以下是 2024-04-02T23:05:34.056403 运行 的最新结果：

python { "all": { "acc": 0.5983124647703518, "acc_stderr": 0.033291497478010114, "acc_norm": 0.6004676655368621, "acc_norm_stderr": 0.03397339563736216, "mc1": 0.5997552019583844, "mc1_stderr": 0.017151605555749138, "mc2": 0.7523411101488666, "mc2_stderr": 0.01424069152084373 }, "harness|arc:challenge|25": { "acc": 0.6680887372013652, "acc_stderr": 0.01376098820088054, "acc_norm": 0.7030716723549488, "acc_norm_stderr": 0.013352025976725222 }, "harness|hellaswag|10": { "acc": 0.663612826130253, "acc_stderr": 0.004715075119834512, "acc_norm": 0.8681537542322246, "acc_norm_stderr": 0.003376320955916706 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "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": 0.6381578947368421, "acc_stderr": 0.03910525752849725, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849725 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "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": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "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": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "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": 0.04292346959909282, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.502127659574468, "acc_stderr": 0.032685726586674915, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.032685726586674915 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070434, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070434 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5172413793103449, "acc_stderr": 0.04164188720169375, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.04164188720169375 }, "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": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "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": 0.6193548387096774, "acc_stderr": 0.02762171783290704, "acc_norm": 0.6193548387096774, "acc_norm_stderr": 0.02762171783290704 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.03486731727419873, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419873 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.0347769116216366, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124484, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124484 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8549222797927462, "acc_stderr": 0.025416343096306422, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.025416343096306422 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5948717948717949, "acc_stderr": 0.024890471769938145, "acc_norm": 0.5948717948717949, "acc_norm_stderr": 0.024890471769938145 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.27037037037037037, "acc_stderr": 0.02708037281514567, "acc_norm": 0.27037037037037037, "acc_norm_stderr": 0.02708037281514567 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6050420168067226, "acc_stderr": 0.03175367846096625, "acc_norm": 0.6050420168067