open-llm-leaderboard-old/details_Weyaxi__very-test
收藏数据集概述
数据集来源
该数据集是在评估模型 Weyaxi/very-test 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
以下是加载运行细节的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Weyaxi__very-test", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-02T11:08:50.720167 运行的最新结果： python { "all": { "acc": 0.621240021862014, "acc_stderr": 0.032135488932384076, "acc_norm": 0.6323055902860398, "acc_norm_stderr": 0.03292467379464547, "mc1": 0.2876376988984088, "mc1_stderr": 0.01584631510139481, "mc2": 0.44279159783454264, "mc2_stderr": 0.015167006349063972 }, "harness|arc:challenge|25": { "acc": 0.5998293515358362, "acc_stderr": 0.014317197787809172, "acc_norm": 0.6390784982935154, "acc_norm_stderr": 0.014034761386175452 }, "harness|hellaswag|10": { "acc": 0.6256721768571998, "acc_stderr": 0.004829598101635787, "acc_norm": 0.8170683130850428, "acc_norm_stderr": 0.0038582038518199338 }, "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": 0.5703703703703704, "acc_stderr": 0.04276349494376599, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119668, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119668 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6679245283018868, "acc_stderr": 0.02898545565233439, "acc_norm": 0.6679245283018868, "acc_norm_stderr": 0.02898545565233439 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.04975698519562428, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "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": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266344, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266344 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5446808510638298, "acc_stderr": 0.032555253593403555, "acc_norm": 0.5446808510638298, "acc_norm_stderr": 0.032555253593403555 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4126984126984127, "acc_stderr": 0.02535574126305527, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.02535574126305527 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.26, "acc_stderr": 0.044084400227680794, "acc_norm": 0.26, "acc_norm_stderr": 0.044084400227680794 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7709677419354839, "acc_stderr": 0.023904914311782655, "acc_norm": 0.7709677419354839, "acc_norm_stderr": 0.023904914311782655 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.032568666616811015, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.032568666616811015 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121417, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121417 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6205128205128205, "acc_stderr": 0.024603626924097424, "acc_norm": 0.6205128205128205, "acc_norm_stderr": 0.024603626924097424 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948492, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.02874204
