open-llm-leaderboard-old/details_cloudyu__TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO_f16
收藏数据集概述
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。数据集是从1次运行中创建的,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。
额外配置
一个额外的配置"results"存储所有运行的聚合结果,用于计算并在Open LLM Leaderboard上显示聚合指标。
最新结果
以下是2024-02-04T00:31:33.025803运行的最新结果:
python { "all": { "acc": 0.764901672440236, "acc_stderr": 0.02826230862515645, "acc_norm": 0.7677453718421197, "acc_norm_stderr": 0.02881226227160178, "mc1": 0.5556915544675642, "mc1_stderr": 0.017394586250743176, "mc2": 0.7224126373641326, "mc2_stderr": 0.014009811551091062 }, "harness|arc:challenge|25": { "acc": 0.7218430034129693, "acc_stderr": 0.0130944699195388, "acc_norm": 0.7406143344709898, "acc_norm_stderr": 0.012808273573927094 }, "harness|hellaswag|10": { "acc": 0.6701852220673172, "acc_stderr": 0.004691848665399069, "acc_norm": 0.8673571001792472, "acc_norm_stderr": 0.003384951803213475 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.875, "acc_stderr": 0.026913523521537846, "acc_norm": 0.875, "acc_norm_stderr": 0.026913523521537846 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8075471698113208, "acc_stderr": 0.024262979839372274, "acc_norm": 0.8075471698113208, "acc_norm_stderr": 0.024262979839372274 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.025545239210256917, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.025545239210256917 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.44, "acc_stderr": 0.0498887651569859, "acc_norm": 0.44, "acc_norm_stderr": 0.0498887651569859 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7167630057803468, "acc_stderr": 0.034355680560478746, "acc_norm": 0.7167630057803468, "acc_norm_stderr": 0.034355680560478746 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5196078431372549, "acc_stderr": 0.04971358884367406, "acc_norm": 0.5196078431372549, "acc_norm_stderr": 0.04971358884367406 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7617021276595745, "acc_stderr": 0.02785125297388977, "acc_norm": 0.7617021276595745, "acc_norm_stderr": 0.02785125297388977 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7517241379310344, "acc_stderr": 0.036001056927277696, "acc_norm": 0.7517241379310344, "acc_norm_stderr": 0.036001056927277696 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7433862433862434, "acc_stderr": 0.022494510767503154, "acc_norm": 0.7433862433862434, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04444444444444449, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9064516129032258, "acc_stderr": 0.016565754668270982, "acc_norm": 0.9064516129032258, "acc_norm_stderr": 0.016565754668270982 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6650246305418719, "acc_stderr": 0.033208527423483104, "acc_norm": 0.6650246305418719, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8848484848484849, "acc_stderr": 0.024925699798115344, "acc_norm": 0.8848484848484849, "acc_norm_stderr": 0.024925699798115344 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9292929292929293, "acc_stderr": 0.01826310542019949, "acc_norm": 0.9292929292929293, "acc_norm_stderr": 0.01826310542019949 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9740932642487047, "acc_stderr": 0.011464523356953162, "acc_norm": 0.9740932642487047, "acc_norm_stderr": 0.011464523356953162 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.019880165406588796, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.019880165406588796 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4444444444444444, "acc_stderr": 0.030296771286067323, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.030296771286067323 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8361344537815126, "acc_stderr": 0.024044054940440488, "acc_norm": 0.8361344537815126, "acc_norm_stderr": 0.024044054940440488 }, "harness|hendrycksTest-high_school_physics|5": {



