open-llm-leaderboard-old/details_brucethemoose__Yi-34B-200K-DARE-merge-v5
收藏数据集概述
数据集名称
Evaluation run of brucethemoose/Yi-34B-200K-DARE-merge-v5
数据集摘要
该数据集是在模型 brucethemoose/Yi-34B-200K-DARE-merge-v5 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，每次运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_brucethemoose__Yi-34B-200K-DARE-merge-v5", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2023-12-24T23:49:50.137882 的运行： python { "all": { "acc": 0.7667764662598182, "acc_stderr": 0.0279506982164214, "acc_norm": 0.7718008025916722, "acc_norm_stderr": 0.02846678033491038, "mc1": 0.41615667074663404, "mc1_stderr": 0.017255657502903043, "mc2": 0.5745773589644305, "mc2_stderr": 0.015485111485623915 }, "harness|arc:challenge|25": { "acc": 0.64419795221843, "acc_stderr": 0.01399057113791876, "acc_norm": 0.6646757679180887, "acc_norm_stderr": 0.013796182947785562 }, "harness|hellaswag|10": { "acc": 0.6613224457279426, "acc_stderr": 0.004722928332834054, "acc_norm": 0.8554072893845848, "acc_norm_stderr": 0.0035097096477918394 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7407407407407407, "acc_stderr": 0.03785714465066653, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.03785714465066653 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.02564834125169361, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.02564834125169361 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8188679245283019, "acc_stderr": 0.023702963526757798, "acc_norm": 0.8188679245283019, "acc_norm_stderr": 0.023702963526757798 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.025545239210256917, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.025545239210256917 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7572254335260116, "acc_stderr": 0.0326926380614177, "acc_norm": 0.7572254335260116, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5490196078431373, "acc_stderr": 0.04951218252396262, "acc_norm": 0.5490196078431373, "acc_norm_stderr": 0.04951218252396262 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.83, "acc_stderr": 0.03775251680686371, "acc_norm": 0.83, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7872340425531915, "acc_stderr": 0.026754391348039787, "acc_norm": 0.7872340425531915, "acc_norm_stderr": 0.026754391348039787 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.631578947368421, "acc_stderr": 0.04537815354939391, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.04537815354939391 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7862068965517242, "acc_stderr": 0.03416520447747548, "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.03416520447747548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.7222222222222222, "acc_stderr": 0.02306818884826112, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.02306818884826112 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5714285714285714, "acc_stderr": 0.04426266681379909, "acc_norm": 0.5714285714285714, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.9129032258064517, "acc_stderr": 0.016041100741696682, "acc_norm": 0.9129032258064517, "acc_norm_stderr": 0.016041100741696682 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6600985221674877, "acc_stderr": 0.033327690684107895, "acc_norm": 0.6600985221674877, "acc_norm_stderr": 0.033327690684107895 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.83, "acc_stderr": 0.0377525168068637, "acc_norm": 0.83, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8606060606060606, "acc_stderr": 0.0270459488258654, "acc_norm": 0.8606060606060606, "acc_norm_stderr": 0.0270459488258654 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9242424242424242, "acc_stderr": 0.018852670234993093, "acc_norm": 0.9242424242424242, "acc_norm_stderr": 0.018852670234993093 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9792746113989638, "acc_stderr": 0.010281417011909039, "acc_norm": 0.9792746113989638, "acc_norm_stderr": 0.010281417011909039 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8128205128205128, "acc_stderr": 0.01977660108655004, "acc_norm": 0.8128205128205128, "acc_norm_stderr": 0.01977660108655004 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.43333333333333335, "acc_stderr": 0.030213340289237924, "acc_norm": 0.43333333333333335, "acc_norm_stderr":
