open-llm-leaderboard-old/details_lodrick-the-lafted__Winged-Lagomorph-2x13B

该数据集是在模型 lodrick-the-lafted/Winged-Lagomorph-2x13B 在 Open LLM Leaderboard 上进行评估时自动生成的。数据集由 63 个配置组成，每个配置对应一个被评估的任务。数据集包含一次运行的结果，每次运行在每个配置中表示为特定的分割，分割名称使用运行的时间戳。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了运行的所有聚合结果，这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了如何使用 Python 中的 datasets 库加载运行细节的示例。

原始信息汇总

数据集概述

该数据集是在对模型lodrick-the-lafted/Winged-Lagomorph-2x13B进行评估运行时自动创建的，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_lodrick-the-lafted__Winged-Lagomorph-2x13B", "harness_winogrande_5", split="train")

最新结果

以下是2024-01-17T18:07:01.785781运行的最新结果： python { "all": { "acc": 0.44701093892342236, "acc_stderr": 0.03445607638165826, "acc_norm": 0.44980402546373816, "acc_norm_stderr": 0.03519159952391745, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608763, "mc2": 0.4453666576267616, "mc2_stderr": 0.015036118833065276 }, "harness|arc:challenge|25": { "acc": 0.44795221843003413, "acc_stderr": 0.01453201149821167, "acc_norm": 0.47952218430034127, "acc_norm_stderr": 0.014599131353035005 }, "harness|hellaswag|10": { "acc": 0.5243975303724357, "acc_stderr": 0.004983837641502894, "acc_norm": 0.6938856801433977, "acc_norm_stderr": 0.004599358920909553 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.35555555555555557, "acc_stderr": 0.04135176749720386, "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.42105263157894735, "acc_stderr": 0.040179012759817494, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.040179012759817494 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.44150943396226416, "acc_stderr": 0.030561590426731837, "acc_norm": 0.44150943396226416, "acc_norm_stderr": 0.030561590426731837 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.375, "acc_stderr": 0.04048439222695598, "acc_norm": 0.375, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3988439306358382, "acc_stderr": 0.037336266553835096, "acc_norm": 0.3988439306358382, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077636, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.425531914893617, "acc_stderr": 0.032321469162244675, "acc_norm": 0.425531914893617, "acc_norm_stderr": 0.032321469162244675 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.04227054451232199, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.04227054451232199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.29894179894179895, "acc_stderr": 0.023577604791655802, "acc_norm": 0.29894179894179895, "acc_norm_stderr": 0.023577604791655802 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.04006168083848878, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.04006168083848878 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110175, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110175 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4096774193548387, "acc_stderr": 0.027976054915347364, "acc_norm": 0.4096774193548387, "acc_norm_stderr": 0.027976054915347364 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.32019704433497537, "acc_stderr": 0.032826493853041504, "acc_norm": 0.32019704433497537, "acc_norm_stderr": 0.032826493853041504 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5696969696969697, "acc_stderr": 0.03866225962879077, "acc_norm": 0.5696969696969697, "acc_norm_stderr": 0.03866225962879077 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5606060606060606, "acc_stderr": 0.035360859475294805, "acc_norm": 0.5606060606060606, "acc_norm_stderr": 0.035360859475294805 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5440414507772021, "acc_stderr": 0.03594413711272438, "acc_norm": 0.5440414507772021, "acc_norm_stderr": 0.03594413711272438 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.023901157979402538, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.023901157979402538 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2777777777777778, "acc_stderr": 0.027309140588230186, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.027309140588230186 }, "