open-llm-leaderboard-old/details_KatyTheCutie__EstopianMaid-13B
收藏数据集概述
数据集简介
该数据集是在评估模型 KatyTheCutie/EstopianMaid-13B 在 Open LLM Leaderboard 上的自动创建的。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 1 次运行创建，每个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" 存储所有运行结果的聚合，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_KatyTheCutie__EstopianMaid-13B", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自 2024-02-14T11:59:41.203334 的运行： python { "all": { "acc": 0.5588896471810725, "acc_stderr": 0.03358524149192356, "acc_norm": 0.5671325395608912, "acc_norm_stderr": 0.034363791698055104, "mc1": 0.3537331701346389, "mc1_stderr": 0.016737814358846147, "mc2": 0.5235005454748325, "mc2_stderr": 0.01582550300012819 }, "harness|arc:challenge|25": { "acc": 0.5836177474402731, "acc_stderr": 0.014405618279436178, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938169 }, "harness|hellaswag|10": { "acc": 0.6406094403505278, "acc_stderr": 0.004788412062375697, "acc_norm": 0.8348934475204143, "acc_norm_stderr": 0.0037051790292873302 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5111111111111111, "acc_stderr": 0.04318275491977976, "acc_norm": 0.5111111111111111, "acc_norm_stderr": 0.04318275491977976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5328947368421053, "acc_stderr": 0.040601270352363966, "acc_norm": 0.5328947368421053, "acc_norm_stderr": 0.040601270352363966 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5886792452830188, "acc_stderr": 0.030285009259009787, "acc_norm": 0.5886792452830188, "acc_norm_stderr": 0.030285009259009787 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04076663253918567, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04076663253918567 }, "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": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5144508670520231, "acc_stderr": 0.03810871630454764, "acc_norm": 0.5144508670520231, "acc_norm_stderr": 0.03810871630454764 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808777, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808777 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.04461960433384739, "acc_norm": 0.73, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.032579014820998356, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.032579014820998356 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.041665675771015785, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3148148148148148, "acc_stderr": 0.023919984164047736, "acc_norm": 0.3148148148148148, "acc_norm_stderr": 0.023919984164047736 }, "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": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6483870967741936, "acc_stderr": 0.02716253782694846, "acc_norm": 0.6483870967741936, "acc_norm_stderr": 0.02716253782694846 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43842364532019706, "acc_stderr": 0.03491207857486518, "acc_norm": 0.43842364532019706, "acc_norm_stderr": 0.03491207857486518 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.0368105086916155, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0368105086916155 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.702020202020202, "acc_stderr": 0.03258630383836556, "acc_norm": 0.702020202020202, "acc_norm_stderr": 0.03258630383836556 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8082901554404145, "acc_stderr": 0.02840895362624526, "acc_norm": 0.8082901554404145, "acc_norm_stderr": 0.02840895362624526 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5102564102564102, "acc_stderr": 0.025345672221942374, "acc_norm": 0.5102564102564102, "acc_norm_stderr": 0.025345672221942374 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945277, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.027420019350945277 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5714285714285714,
