open-llm-leaderboard-old/details_JaeyeonKang__CCK_Gony_v3.2
收藏数据集概述
数据集简介
该数据集是在模型 JaeyeonKang/CCK_Gony_v3.2 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 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 3 次运行中创建，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。
- 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_JaeyeonKang__CCK_Gony_v3.2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-02T09:25:22.859036 运行 的最新结果：
python { "all": { "acc": 0.7047084782513622, "acc_stderr": 0.030315860999845592, "acc_norm": 0.7093203962624949, "acc_norm_stderr": 0.030894611332654892, "mc1": 0.4418604651162791, "mc1_stderr": 0.017384767478986218, "mc2": 0.5881032370657441, "mc2_stderr": 0.015065851872175183 }, "harness|arc:challenge|25": { "acc": 0.6467576791808873, "acc_stderr": 0.013967822714840055, "acc_norm": 0.6945392491467577, "acc_norm_stderr": 0.013460080478002508 }, "harness|hellaswag|10": { "acc": 0.6735710017924716, "acc_stderr": 0.004679479763516775, "acc_norm": 0.8691495717984465, "acc_norm_stderr": 0.003365474860676741 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411021, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411021 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6888888888888889, "acc_stderr": 0.039992628766177214, "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.039992628766177214 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7960526315789473, "acc_stderr": 0.0327900040631005, "acc_norm": 0.7960526315789473, "acc_norm_stderr": 0.0327900040631005 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542127, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.769811320754717, "acc_stderr": 0.02590789712240817, "acc_norm": 0.769811320754717, "acc_norm_stderr": 0.02590789712240817 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8541666666666666, "acc_stderr": 0.029514245964291766, "acc_norm": 0.8541666666666666, "acc_norm_stderr": 0.029514245964291766 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.63, "acc_stderr": 0.048523658709391, "acc_norm": 0.63, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7456647398843931, "acc_stderr": 0.03320556443085569, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.03320556443085569 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.04878608714466996, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.04878608714466996 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036845, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6553191489361702, "acc_stderr": 0.03106898596312215, "acc_norm": 0.6553191489361702, "acc_norm_stderr": 0.03106898596312215 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5789473684210527, "acc_stderr": 0.046446020912223177, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6689655172413793, "acc_stderr": 0.03921545312467122, "acc_norm": 0.6689655172413793, "acc_norm_stderr": 0.03921545312467122 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.49206349206349204, "acc_stderr": 0.025748065871673272, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.025748065871673272 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8548387096774194, "acc_stderr": 0.020039563628053283, "acc_norm": 0.8548387096774194, "acc_norm_stderr": 0.020039563628053283 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5911330049261084, "acc_stderr": 0.034590588158832314, "acc_norm": 0.5911330049261084, "acc_norm_stderr": 0.034590588158832314 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.0315841532404771, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.0315841532404771 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343336, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343336 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9481865284974094, "acc_stderr": 0.01599622932024412, "acc_norm": 0.9481865284974094, "acc_norm_stderr": 0.01599622932024412 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7153846153846154, "acc_stderr": 0.0228783227997063, "acc_norm": 0.7153846153846154, "acc_norm_stderr": 0.0228783227997063 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35555555555555557, "acc_stderr": 0.0291857149498574, "acc_norm": 0.35555555555555557, "acc_norm_stderr
