open-llm-leaderboard-old/details_umd-zhou-lab__recycled-alpaca-7b-v2.0
收藏数据集概述
该数据集是在评估模型umd-zhou-lab/recycled-alpaca-7b-v2.0在Open LLM Leaderboard上的运行过程中自动创建的。
数据集组成
- 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。
- 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_umd-zhou-lab__recycled-alpaca-7b-v2.0", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自2024-01-10T17:08:53.842627的运行： python { "all": { "acc": 0.4686343258788306, "acc_stderr": 0.03447664010622075, "acc_norm": 0.4744437973313396, "acc_norm_stderr": 0.0352708768291591, "mc1": 0.2974296205630355, "mc1_stderr": 0.016002651487361005, "mc2": 0.4539882338054229, "mc2_stderr": 0.01568479961738538 }, "harness|arc:challenge|25": { "acc": 0.5034129692832765, "acc_stderr": 0.014611050403244081, "acc_norm": 0.5418088737201365, "acc_norm_stderr": 0.0145602203087147 }, "harness|hellaswag|10": { "acc": 0.5908185620394344, "acc_stderr": 0.004906779523192672, "acc_norm": 0.7798247361083449, "acc_norm_stderr": 0.004135178705231737 }, "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": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4342105263157895, "acc_stderr": 0.040335656678483205, "acc_norm": 0.4342105263157895, "acc_norm_stderr": 0.040335656678483205 }, "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": 0.5547169811320755, "acc_stderr": 0.030588052974270658, "acc_norm": 0.5547169811320755, "acc_norm_stderr": 0.030588052974270658 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4375, "acc_stderr": 0.04148415739394154, "acc_norm": 0.4375, "acc_norm_stderr": 0.04148415739394154 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3930635838150289, "acc_stderr": 0.0372424959581773, "acc_norm": 0.3930635838150289, "acc_norm_stderr": 0.0372424959581773 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.1568627450980392, "acc_stderr": 0.03618664819936246, "acc_norm": 0.1568627450980392, "acc_norm_stderr": 0.03618664819936246 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.37872340425531914, "acc_stderr": 0.03170995606040655, "acc_norm": 0.37872340425531914, "acc_norm_stderr": 0.03170995606040655 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4896551724137931, "acc_stderr": 0.04165774775728763, "acc_norm": 0.4896551724137931, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.30423280423280424, "acc_stderr": 0.023695415009463087, "acc_norm": 0.30423280423280424, "acc_norm_stderr": 0.023695415009463087 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30158730158730157, "acc_stderr": 0.04104947269903394, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.04104947269903394 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.5064516129032258, "acc_stderr": 0.02844163823354051, "acc_norm": 0.5064516129032258, "acc_norm_stderr": 0.02844163823354051 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3694581280788177, "acc_stderr": 0.03395970381998574, "acc_norm": 0.3694581280788177, "acc_norm_stderr": 0.03395970381998574 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03756335775187897, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03756335775187897 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5454545454545454, "acc_stderr": 0.03547601494006938, "acc_norm": 0.5454545454545454, "acc_norm_stderr": 0.03547601494006938 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6373056994818653, "acc_stderr": 0.03469713791704372, "acc_norm": 0.6373056994818653, "acc_norm_stderr": 0.03469713791704372 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4307692307692308, "acc_stderr": 0.02510682066053975, "acc_norm": 0.4307692307692308, "acc_norm_stderr": 0.02510682066053975 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815632, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.028133252578815632 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.42016806722689076, "acc_stderr": 0.0320
