open-llm-leaderboard-old/details_indischepartij__OpenMia-Indo-Mistral-7b-v4
收藏数据集概述
数据集摘要
该数据集是在评估模型 indischepartij/OpenMia-Indo-Mistral-7b-v4 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
数据集由 63 个配置组成，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_indischepartij__OpenMia-Indo-Mistral-7b-v4", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-09T18:06:44.848755 运行的最新结果：
python { "all": { "acc": 0.6114734637288325, "acc_stderr": 0.03296895712670361, "acc_norm": 0.6149636164852647, "acc_norm_stderr": 0.03363578569052238, "mc1": 0.37821297429620565, "mc1_stderr": 0.016976335907546866, "mc2": 0.5335887952185934, "mc2_stderr": 0.015106225408052556 }, "harness|arc:challenge|25": { "acc": 0.5955631399317406, "acc_stderr": 0.014342036483436174, "acc_norm": 0.6416382252559727, "acc_norm_stderr": 0.014012883334859859 }, "harness|hellaswag|10": { "acc": 0.6222863971320454, "acc_stderr": 0.004838246410786271, "acc_norm": 0.8284206333399721, "acc_norm_stderr": 0.003762439284195103 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849724, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849724 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7056603773584905, "acc_stderr": 0.02804918631569525, "acc_norm": 0.7056603773584905, "acc_norm_stderr": 0.02804918631569525 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.037455547914624555, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.037455547914624555 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "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": 0.5895953757225434, "acc_stderr": 0.03750757044895537, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.502127659574468, "acc_stderr": 0.032685726586674915, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.032685726586674915 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482757, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.025379524910778408, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.025379524910778408 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7161290322580646, "acc_stderr": 0.02564938106302926, "acc_norm": 0.7161290322580646, "acc_norm_stderr": 0.02564938106302926 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7151515151515152, "acc_stderr": 0.03524390844511781, "acc_norm": 0.7151515151515152, "acc_norm_stderr": 0.03524390844511781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164528, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164528 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6025641025641025, "acc_stderr": 0.024811920017903836, "acc_norm": 0.6025641025641025, "acc_norm_stderr": 0.024811920017903836 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815632,
