open-llm-leaderboard-old/details_Changgil__k2s3_test_24001
收藏数据集概述
该数据集是在模型 Changgil/k2s3_test_24001 在 Open LLM Leaderboard 上的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。
数据集结构
数据集由 2 次运行创建，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。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Changgil__k2s3_test_24001", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-15T07:38:41.232311 运行的最新结果：
python { "all": { "acc": 0.5457607639419929, "acc_stderr": 0.03381228856533623, "acc_norm": 0.5506067592536232, "acc_norm_stderr": 0.03452302087358302, "mc1": 0.2864137086903305, "mc1_stderr": 0.015826142439502342, "mc2": 0.4357245447683409, "mc2_stderr": 0.01457057655258036 }, "harness|arc:challenge|25": { "acc": 0.5136518771331058, "acc_stderr": 0.014605943429860947, "acc_norm": 0.5571672354948806, "acc_norm_stderr": 0.014515573873348902 }, "harness|hellaswag|10": { "acc": 0.6011750647281418, "acc_stderr": 0.004886559008754983, "acc_norm": 0.8069109739095798, "acc_norm_stderr": 0.003939155484500657 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411022, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411022 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5407407407407407, "acc_stderr": 0.04304979692464242, "acc_norm": 0.5407407407407407, "acc_norm_stderr": 0.04304979692464242 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490437, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490437 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6037735849056604, "acc_stderr": 0.030102793781791197, "acc_norm": 0.6037735849056604, "acc_norm_stderr": 0.030102793781791197 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5694444444444444, "acc_stderr": 0.04140685639111503, "acc_norm": 0.5694444444444444, "acc_norm_stderr": 0.04140685639111503 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.48554913294797686, "acc_stderr": 0.03810871630454764, "acc_norm": 0.48554913294797686, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3235294117647059, "acc_stderr": 0.046550104113196177, "acc_norm": 0.3235294117647059, "acc_norm_stderr": 0.046550104113196177 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3829787234042553, "acc_stderr": 0.03177821250236922, "acc_norm": 0.3829787234042553, "acc_norm_stderr": 0.03177821250236922 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.335978835978836, "acc_stderr": 0.024326310529149138, "acc_norm": 0.335978835978836, "acc_norm_stderr": 0.024326310529149138 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303317, "acc_norm": 0.30952380952380953, "acc_norm_stderr": 0.04134913018303317 }, "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": 0.6548387096774193, "acc_stderr": 0.027045746573534327, "acc_norm": 0.6548387096774193, "acc_norm_stderr": 0.027045746573534327 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4236453201970443, "acc_stderr": 0.03476725747649037, "acc_norm": 0.4236453201970443, "acc_norm_stderr": 0.03476725747649037 }, "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": 0.6606060606060606, "acc_stderr": 0.03697442205031595, "acc_norm": 0.6606060606060606, "acc_norm_stderr": 0.03697442205031595 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6868686868686869, "acc_stderr": 0.033042050878136525, "acc_norm": 0.6868686868686869, "acc_norm_stderr": 0.033042050878136525 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7668393782383419, "acc_stderr": 0.03051611137147602, "acc_norm": 0.7668393782383419, "acc_norm_stderr": 0.03051611137147602 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5076923076923077, "acc_stderr": 0.025348006031534778, "acc_norm": 0.5076923076923077, "acc_norm_stderr": 0.025348006031534778 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.0279404571362284, "acc_norm": 0.3, "acc_norm_stderr": 0.0279404571362284 }, "har
