open-llm-leaderboard-old/details_athirdpath__Orca-2-13b-Alpaca-Uncensored
收藏数据集概述
数据集简介
该数据集是在对模型 athirdpath/Orca-2-13b-Alpaca-Uncensored 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
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。数据集是从 1 次运行中创建的，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。
额外配置
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 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_athirdpath__Orca-2-13b-Alpaca-Uncensored", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-17T14:58:45.053086 运行的最新结果：
python { "all": { "acc": 0.6002703838763287, "acc_stderr": 0.032941926494755115, "acc_norm": 0.6047089287996544, "acc_norm_stderr": 0.03361522848210774, "mc1": 0.37821297429620565, "mc1_stderr": 0.01697633590754687, "mc2": 0.5358987502340753, "mc2_stderr": 0.01565060464007792 }, "harness|arc:challenge|25": { "acc": 0.5750853242320819, "acc_stderr": 0.014445698968520769, "acc_norm": 0.6109215017064846, "acc_norm_stderr": 0.014247309976045607 }, "harness|hellaswag|10": { "acc": 0.6100378410675165, "acc_stderr": 0.004867445945277156, "acc_norm": 0.792670782712607, "acc_norm_stderr": 0.004045648954769832 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7302631578947368, "acc_stderr": 0.036117805602848975, "acc_norm": 0.7302631578947368, "acc_norm_stderr": 0.036117805602848975 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6150943396226415, "acc_stderr": 0.02994649856769995, "acc_norm": 0.6150943396226415, "acc_norm_stderr": 0.02994649856769995 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6666666666666666, "acc_stderr": 0.03942082639927213, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.03942082639927213 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5664739884393064, "acc_stderr": 0.03778621079092056, "acc_norm": 0.5664739884393064, "acc_norm_stderr": 0.03778621079092056 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006718, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006718 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5361702127659574, "acc_stderr": 0.03260038511835771, "acc_norm": 0.5361702127659574, "acc_norm_stderr": 0.03260038511835771 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159795, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159795 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.31746031746031744, "acc_stderr": 0.04163453031302859, "acc_norm": 0.31746031746031744, "acc_norm_stderr": 0.04163453031302859 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7387096774193549, "acc_stderr": 0.024993053397764805, "acc_norm": 0.7387096774193549, "acc_norm_stderr": 0.024993053397764805 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.46798029556650245, "acc_stderr": 0.03510766597959217, "acc_norm": 0.46798029556650245, "acc_norm_stderr": 0.03510766597959217 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7151515151515152, "acc_stderr": 0.03524390844511781, "acc_norm": 0.7151515151515152, "acc_norm_stderr": 0.03524390844511781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.030954055470365897, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8549222797927462, "acc_stderr": 0.02541634309630642, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.02541634309630642 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5794871794871795, "acc_stderr": 0.025028610276710855, "acc_norm": 0.5794871794871795, "acc_norm_stderr": 0.025028610276710855 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3296296296296296, "acc_stderr": 0.028661201116524586, "acc_norm": 0.3296296296296296, "acc_norm_stderr": 0.028661201116524586 }, "harness|hend
