open-llm-leaderboard-old/details_Minami-su__IA_14B
收藏数据集概述
该数据集是在对模型 Minami-su/IA_14B 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。
- 额外的 "results" 配置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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Minami-su__IA_14B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-21T15:35:10.890241 运行的最新结果：
python { "all": { "acc": 0.6725231661193563, "acc_stderr": 0.03173694433792602, "acc_norm": 0.6819399785391478, "acc_norm_stderr": 0.03237278026633433, "mc1": 0.43451652386780903, "mc1_stderr": 0.017352738749259564, "mc2": 0.6221767645042083, "mc2_stderr": 0.015637740339447825 }, "harness|arc:challenge|25": { "acc": 0.5836177474402731, "acc_stderr": 0.014405618279436178, "acc_norm": 0.6237201365187713, "acc_norm_stderr": 0.014157022555407161 }, "harness|hellaswag|10": { "acc": 0.6034654451304521, "acc_stderr": 0.004881780399499135, "acc_norm": 0.807010555666202, "acc_norm_stderr": 0.003938382581186512 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6666666666666666, "acc_stderr": 0.04072314811876837, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7236842105263158, "acc_stderr": 0.03639057569952929, "acc_norm": 0.7236842105263158, "acc_norm_stderr": 0.03639057569952929 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7018867924528301, "acc_stderr": 0.02815283794249387, "acc_norm": 0.7018867924528301, "acc_norm_stderr": 0.02815283794249387 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.03533133389323657, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.03533133389323657 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5196078431372549, "acc_stderr": 0.04971358884367405, "acc_norm": 0.5196078431372549, "acc_norm_stderr": 0.04971358884367405 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6510638297872341, "acc_stderr": 0.031158522131357783, "acc_norm": 0.6510638297872341, "acc_norm_stderr": 0.031158522131357783 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6827586206896552, "acc_stderr": 0.03878352372138622, "acc_norm": 0.6827586206896552, "acc_norm_stderr": 0.03878352372138622 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5767195767195767, "acc_stderr": 0.025446365634406776, "acc_norm": 0.5767195767195767, "acc_norm_stderr": 0.025446365634406776 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5476190476190477, "acc_stderr": 0.044518079590553275, "acc_norm": 0.5476190476190477, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.832258064516129, "acc_stderr": 0.021255464065371318, "acc_norm": 0.832258064516129, "acc_norm_stderr": 0.021255464065371318 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5517241379310345, "acc_stderr": 0.03499113137676744, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.03499113137676744 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.04408440022768079, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.02845038880528436, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.02845038880528436 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8535353535353535, "acc_stderr": 0.02519092111460393, "acc_norm": 0.8535353535353535, "acc_norm_stderr": 0.02519092111460393 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033477, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033477 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7102564102564103, "acc_stderr": 0.023000628243687957, "acc_norm": 0.7102564102564103, "acc_norm_stderr": 0.023000628243687957 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4148148148148148, "acc_stderr": 0.03003984245406929, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.03003984245406929 }, "harness|hendrycksTest-high_school_microeconomics|5": {
