open-llm-leaderboard-old/details_OpenBuddy__openbuddy-mixtral-7bx8-v17.2-32k

该数据集是在模型OpenBuddy/openbuddy-mixtral-7bx8-v17.2-32k的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。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。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

数据集简介

该数据集是在模型 OpenBuddy/openbuddy-mixtral-7bx8-v17.2-32k 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
• "train" 分片始终指向最新的结果。
• 一个额外的配置 "results" 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_OpenBuddy__openbuddy-mixtral-7bx8-v17.2-32k", "harness_winogrande_5", split="train")

最新结果

以下是 2024-02-02T09:54:33.456360 运行 的最新结果：

python { "all": { "acc": 0.18431258568628095, "acc_stderr": 0.027127844586126878, "acc_norm": 0.18293847355265097, "acc_norm_stderr": 0.027828083788311676, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299953, "mc2": NaN, "mc2_stderr": NaN }, "harness|arc:challenge|25": { "acc": 0.2696245733788396, "acc_stderr": 0.012968040686869152, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785564 }, "harness|hellaswag|10": { "acc": 0.2717586138219478, "acc_stderr": 0.004439569447407354, "acc_norm": 0.31358295160326627, "acc_norm_stderr": 0.004630008293925626 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.17037037037037037, "acc_stderr": 0.03247781185995593, "acc_norm": 0.17037037037037037, "acc_norm_stderr": 0.03247781185995593 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.13157894736842105, "acc_stderr": 0.027508689533549905, "acc_norm": 0.13157894736842105, "acc_norm_stderr": 0.027508689533549905 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.16226415094339622, "acc_stderr": 0.022691482872035384, "acc_norm": 0.16226415094339622, "acc_norm_stderr": 0.022691482872035384 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.1527777777777778, "acc_stderr": 0.03008574324856568, "acc_norm": 0.1527777777777778, "acc_norm_stderr": 0.03008574324856568 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.11, "acc_stderr": 0.03144660377352203, "acc_norm": 0.11, "acc_norm_stderr": 0.03144660377352203 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.04093601807403325, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403325 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.1329479768786127, "acc_stderr": 0.02588804297966229, "acc_norm": 0.1329479768786127, "acc_norm_stderr": 0.02588804297966229 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179961, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179961 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2170212765957447, "acc_stderr": 0.026947483121496245, "acc_norm": 0.2170212765957447, "acc_norm_stderr": 0.026947483121496245 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.20175438596491227, "acc_stderr": 0.03775205013583639, "acc_norm": 0.20175438596491227, "acc_norm_stderr": 0.03775205013583639 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2, "acc_stderr": 0.03333333333333331, "acc_norm": 0.2, "acc_norm_stderr": 0.03333333333333331 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.22486772486772486, "acc_stderr": 0.02150209607822914, "acc_norm": 0.22486772486772486, "acc_norm_stderr": 0.02150209607822914 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.035670166752768635, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.035670166752768635 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.16, "acc_stderr": 0.03684529491774709, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.13225806451612904, "acc_stderr": 0.019272015434846485, "acc_norm": 0.13225806451612904, "acc_norm_stderr": 0.019272015434846485 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.1625615763546798, "acc_stderr": 0.025960300064605608, "acc_norm": 0.1625615763546798, "acc_norm_stderr": 0.025960300064605608 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.13333333333333333, "acc_stderr": 0.026544435312706463, "acc_norm": 0.13333333333333333, "acc_norm_stderr": 0.026544435312706463 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.15151515151515152, "acc_stderr": 0.02554565042660359, "acc_norm": 0.15151515151515152, "acc_norm_stderr": 0.02554565042660359 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.16062176165803108, "acc_stderr": 0.026499057701397464, "acc_norm": 0.16062176165803108, "acc_norm_stderr": 0.026499057701397464 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.018895524482604946, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.018895524482604946 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.02578787422095932, "acc_norm": 0.23333333333333