open-llm-leaderboard-old/details_RESMPDEV__Gemma-Wukong-2b
收藏数据集概述
数据集简介
该数据集是在评估模型 RESMPDEV/Gemma-Wukong-2b 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行结果组成，每个运行结果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，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
最新结果
以下是 2024-03-02T03:03:10.199714 运行的最新结果：
python { "all": { "acc": 0.3831572150396804, "acc_stderr": 0.034077698841351076, "acc_norm": 0.38708705016212447, "acc_norm_stderr": 0.03485851209755768, "mc1": 0.2778457772337821, "mc1_stderr": 0.01568092936402465, "mc2": 0.4429426283623105, "mc2_stderr": 0.014956758030618461 }, "harness|arc:challenge|25": { "acc": 0.4249146757679181, "acc_stderr": 0.014445698968520769, "acc_norm": 0.45307167235494883, "acc_norm_stderr": 0.01454689205200563 }, "harness|hellaswag|10": { "acc": 0.5052778331009758, "acc_stderr": 0.004989503417767287, "acc_norm": 0.6693885680143398, "acc_norm_stderr": 0.00469471891822576 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3851851851851852, "acc_stderr": 0.04203921040156279, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3618421052631579, "acc_stderr": 0.03910525752849724, "acc_norm": 0.3618421052631579, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.44150943396226416, "acc_stderr": 0.030561590426731837, "acc_norm": 0.44150943396226416, "acc_norm_stderr": 0.030561590426731837 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04076663253918567, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3179190751445087, "acc_stderr": 0.03550683989165582, "acc_norm": 0.3179190751445087, "acc_norm_stderr": 0.03550683989165582 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4206896551724138, "acc_stderr": 0.0411391498118926, "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2724867724867725, "acc_stderr": 0.02293097307163335, "acc_norm": 0.2724867724867725, "acc_norm_stderr": 0.02293097307163335 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03718489006818114, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03718489006818114 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.42258064516129035, "acc_stderr": 0.02810096472427264, "acc_norm": 0.42258064516129035, "acc_norm_stderr": 0.02810096472427264 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.33004926108374383, "acc_stderr": 0.033085304262282574, "acc_norm": 0.33004926108374383, "acc_norm_stderr": 0.033085304262282574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.44242424242424244, "acc_stderr": 0.03878372113711275, "acc_norm": 0.44242424242424244, "acc_norm_stderr": 0.03878372113711275 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4090909090909091, "acc_stderr": 0.03502975799413007, "acc_norm": 0.4090909090909091, "acc_norm_stderr": 0.03502975799413007 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.45595854922279794, "acc_stderr": 0.035944137112724366, "acc_norm": 0.45595854922279794, "acc_norm_stderr": 0.035944137112724366 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3153846153846154, "acc_stderr": 0.02355964698318995, "acc_norm": 0.3153846153846154, "acc_norm_stderr": 0.02355964698318995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24444444444444444, "acc_stderr": 0.02620276653465215, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.02620276653465215 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.323529411764705
