open-llm-leaderboard-old/details_Azure99__blossom-v5-llama3-8b
收藏数据集概述
数据集简介
该数据集是在评估模型 Azure99/blossom-v5-llama3-8b 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。
额外配置
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_Azure99__blossom-v5-llama3-8b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-20T13:22:39.661617 运行的最新结果：
python { "all": { "acc": 0.6510315333012048, "acc_stderr": 0.03199119247875236, "acc_norm": 0.6563503433064471, "acc_norm_stderr": 0.03262745936738262, "mc1": 0.401468788249694, "mc1_stderr": 0.017160273901693654, "mc2": 0.5712054383937213, "mc2_stderr": 0.015371161430571795 }, "harness|arc:challenge|25": { "acc": 0.5281569965870307, "acc_stderr": 0.014588204105102202, "acc_norm": 0.568259385665529, "acc_norm_stderr": 0.014474591427196202 }, "harness|hellaswag|10": { "acc": 0.6308504282015535, "acc_stderr": 0.004815882719278385, "acc_norm": 0.8305118502290381, "acc_norm_stderr": 0.0037441574425365618 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7171052631578947, "acc_stderr": 0.03665349695640767, "acc_norm": 0.7171052631578947, "acc_norm_stderr": 0.03665349695640767 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7509433962264151, "acc_stderr": 0.026616482980501704, "acc_norm": 0.7509433962264151, "acc_norm_stderr": 0.026616482980501704 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7430555555555556, "acc_stderr": 0.03653946969442099, "acc_norm": 0.7430555555555556, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "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": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4803921568627451, "acc_stderr": 0.04971358884367405, "acc_norm": 0.4803921568627451, "acc_norm_stderr": 0.04971358884367405 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.0325005368436584, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5614035087719298, "acc_stderr": 0.04668000738510455, "acc_norm": 0.5614035087719298, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02530590624159063, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02530590624159063 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5238095238095238, "acc_stderr": 0.04467062628403273, "acc_norm": 0.5238095238095238, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7516129032258064, "acc_stderr": 0.024580028921481003, "acc_norm": 0.7516129032258064, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.0351760354036101, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.0351760354036101 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.03225078108306289, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7878787878787878, "acc_stderr": 0.029126522834586808, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586808 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.02381447708659355, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.02381447708659355 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6333333333333333, "acc_stderr": 0.024433016466052462, "acc_norm": 0.6333333333333333, "acc_norm_stderr": 0.024433016466052462 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34074074074074073, "acc_stderr": 0.02889774874113113, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.0
