open-llm-leaderboard-old/details_fblgit__una-llama-7b
收藏数据集概述
数据集简介
该数据集是在评估模型 fblgit/una-llama-7b 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。
结果配置
一个额外的配置 "results" 存储了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_fblgit__una-llama-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-24T17:39:22.935807 运行的最新结果：
python { "all": { "acc": 0.380732359519661, "acc_stderr": 0.034121438696938955, "acc_norm": 0.3837076059961357, "acc_norm_stderr": 0.03491178592677983, "mc1": 0.2558139534883721, "mc1_stderr": 0.01527417621928336, "mc2": 0.38012253018489384, "mc2_stderr": 0.014122907654663121 }, "harness|arc:challenge|25": { "acc": 0.49658703071672355, "acc_stderr": 0.014611050403244084, "acc_norm": 0.5366894197952219, "acc_norm_stderr": 0.014572000527756986 }, "harness|hellaswag|10": { "acc": 0.599681338378809, "acc_stderr": 0.004889615413144194, "acc_norm": 0.8007369049990042, "acc_norm_stderr": 0.003986299037840092 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720685, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720685 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.32592592592592595, "acc_stderr": 0.040491220417025055, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3815789473684211, "acc_stderr": 0.03953173377749194, "acc_norm": 0.3815789473684211, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4037735849056604, "acc_stderr": 0.03019761160019795, "acc_norm": 0.4037735849056604, "acc_norm_stderr": 0.03019761160019795 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3263888888888889, "acc_stderr": 0.03921067198982266, "acc_norm": 0.3263888888888889, "acc_norm_stderr": 0.03921067198982266 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3352601156069364, "acc_stderr": 0.03599586301247077, "acc_norm": 0.3352601156069364, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3574468085106383, "acc_stderr": 0.03132941789476425, "acc_norm": 0.3574468085106383, "acc_norm_stderr": 0.03132941789476425 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159393, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159393 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.296551724137931, "acc_stderr": 0.03806142687309993, "acc_norm": 0.296551724137931, "acc_norm_stderr": 0.03806142687309993 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2857142857142857, "acc_stderr": 0.023266512213730585, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.023266512213730585 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.04190596438871136, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.04190596438871136 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3774193548387097, "acc_stderr": 0.02757596072327823, "acc_norm": 0.3774193548387097, "acc_norm_stderr": 0.02757596072327823 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.03194740072265541, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.03194740072265541 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.41818181818181815, "acc_stderr": 0.03851716319398393, "acc_norm": 0.41818181818181815, "acc_norm_stderr": 0.03851716319398393 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.40404040404040403, "acc_stderr": 0.03496130972056128, "acc_norm": 0.40404040404040403, "acc_norm_stderr": 0.03496130972056128 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.48704663212435234, "acc_stderr": 0.03607228061047749, "acc_norm": 0.48704663212435234, "acc_norm_stderr": 0.03607228061047749 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.02443301646605245, "acc_norm": 0.36666666666666664, "acc_norm_stderr": 0.02443301646605245 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.025348097468097856, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.02
