open-llm-leaderboard-old/details_ValiantLabs__Fireplace-34b
收藏数据集概述
数据集简介
该数据集是在对模型 ValiantLabs/Fireplace-34b 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，每次运行的详细结果存储在特定的分割中，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" 存储了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 2024-03-28T03:22:05.277187 运行的最新结果：
python { "all": { "acc": 0.4834577683836408, "acc_stderr": 0.03289644268866917, "acc_norm": 0.4802223731928543, "acc_norm_stderr": 0.033565112342065634, "mc1": 0.46511627906976744, "mc1_stderr": 0.017460849975873965, "mc2": 0.6511266679430222, "mc2_stderr": 0.014613962681117974 }, "harness|arc:challenge|25": { "acc": 0.6783276450511946, "acc_stderr": 0.013650488084494162, "acc_norm": 0.712457337883959, "acc_norm_stderr": 0.013226719056266129 }, "harness|hellaswag|10": { "acc": 0.6337382991435969, "acc_stderr": 0.0048079755154464875, "acc_norm": 0.8272256522605059, "acc_norm_stderr": 0.0037727944471851564 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614866, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8092105263157895, "acc_stderr": 0.031975658210325, "acc_norm": 0.8092105263157895, "acc_norm_stderr": 0.031975658210325 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.3132075471698113, "acc_stderr": 0.02854479331905533, "acc_norm": 0.3132075471698113, "acc_norm_stderr": 0.02854479331905533 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3125, "acc_stderr": 0.038760854559127644, "acc_norm": 0.3125, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.30057803468208094, "acc_stderr": 0.03496101481191182, "acc_norm": 0.30057803468208094, "acc_norm_stderr": 0.03496101481191182 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.22549019607843138, "acc_stderr": 0.041583075330832865, "acc_norm": 0.22549019607843138, "acc_norm_stderr": 0.041583075330832865 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102953, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102953 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.41379310344827586, "acc_stderr": 0.04104269211806232, "acc_norm": 0.41379310344827586, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25396825396825395, "acc_stderr": 0.022418042891113953, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.022418042891113953 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.041905964388711366, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.041905964388711366 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8290322580645161, "acc_stderr": 0.021417242936321586, "acc_norm": 0.8290322580645161, "acc_norm_stderr": 0.021417242936321586 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.0317852971064275, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.0317852971064275 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8303030303030303, "acc_stderr": 0.02931118867498312, "acc_norm": 0.8303030303030303, "acc_norm_stderr": 0.02931118867498312 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3383838383838384, "acc_stderr": 0.033711241426263014, "acc_norm": 0.3383838383838384, "acc_norm_stderr": 0.033711241426263014 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7461139896373057, "acc_stderr": 0.0314102478056532, "acc_norm": 0.7461139896373057, "acc_norm_stderr": 0.0314102478056532 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.23076923076923078, "acc_stderr": 0.021362027725222724, "acc_norm": 0.23076923076923078, "acc_norm_stderr": 0.021362027725222724 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073828, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.026962424325073828 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.3865546218487395, "acc_stderr": 0.031631
