open-llm-leaderboard-old/details_maldv__electric-mist-7b
收藏数据集概述
数据集简介
该数据集是在评估模型 maldv/electric-mist-7b 在 Open LLM Leaderboard 上的运行过程中自动创建的。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
- 配置数量：63 个配置
- 数据来源：1 次运行
- 数据分割：每个配置包含特定分割，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："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_maldv__electric-mist-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-29T20:22:45.414201 运行的最新结果：
python { "all": { "acc": 0.5931441068496816, "acc_stderr": 0.03313019969813812, "acc_norm": 0.6011893533111391, "acc_norm_stderr": 0.033818919029840425, "mc1": 0.31334149326805383, "mc1_stderr": 0.016238065069059608, "mc2": 0.453710740888472, "mc2_stderr": 0.014893424963710102 }, "harness|arc:challenge|25": { "acc": 0.5699658703071673, "acc_stderr": 0.014467631559137998, "acc_norm": 0.6117747440273038, "acc_norm_stderr": 0.014241614207414044 }, "harness|hellaswag|10": { "acc": 0.6289583748257319, "acc_stderr": 0.004820962855749743, "acc_norm": 0.8256323441545509, "acc_norm_stderr": 0.0037864988567691206 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "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": 0.631578947368421, "acc_stderr": 0.03925523381052932, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6339622641509434, "acc_stderr": 0.029647813539365245, "acc_norm": 0.6339622641509434, "acc_norm_stderr": 0.029647813539365245 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6069364161849711, "acc_stderr": 0.03724249595817729, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.03724249595817729 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.04560480215720683, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4978723404255319, "acc_stderr": 0.03268572658667492, "acc_norm": 0.4978723404255319, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.025043757318520193, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.025043757318520193 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7096774193548387, "acc_stderr": 0.02582210611941591, "acc_norm": 0.7096774193548387, "acc_norm_stderr": 0.02582210611941591 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885415, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885415 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7373737373737373, "acc_stderr": 0.03135305009533086, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.03135305009533086 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397443, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5743589743589743, "acc_stderr": 0.025069094387296532, "acc_norm": 0.5743589743589743, "acc_norm_stderr": 0.025069094387296532 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.02684205787383371, "acc_norm": 0.26296296296296295, "acc_norm_stderr": 0.02684205787383371 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.57983193277310
