open-llm-leaderboard/details_gpt2-xl
收藏数据集概述
数据集名称
Evaluation run of gpt2-xl
数据集摘要
该数据集是在对模型 gpt2-xl 进行评估运行期间自动创建的，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。
数据集创建
数据集从 3 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_gpt2-xl", "harness_winogrande_5", split="train")
最新结果
这些是最新结果（来自 2023-12-16T14:28:59.235900 运行）的示例： python { "all": { "acc": 0.26849437510168506, "acc_stderr": 0.031366498421091876, "acc_norm": 0.2702003428835176, "acc_norm_stderr": 0.03215444575128815, "mc1": 0.22031823745410037, "mc1_stderr": 0.0145090451714873, "mc2": 0.38536763571053717, "mc2_stderr": 0.014057464412774041 }, "harness|arc:challenge|25": { "acc": 0.2593856655290102, "acc_stderr": 0.012808273573927104, "acc_norm": 0.302901023890785, "acc_norm_stderr": 0.013428241573185347 }, "harness|hellaswag|10": { "acc": 0.3981278629755029, "acc_stderr": 0.004885116465550274, "acc_norm": 0.5136427006572396, "acc_norm_stderr": 0.004987923636628551 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.2074074074074074, "acc_stderr": 0.03502553170678318, "acc_norm": 0.2074074074074074, "acc_norm_stderr": 0.03502553170678318 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.29056603773584905, "acc_stderr": 0.027943219989337145, "acc_norm": 0.29056603773584905, "acc_norm_stderr": 0.027943219989337145 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2847222222222222, "acc_stderr": 0.03773809990686935, "acc_norm": 0.2847222222222222, "acc_norm_stderr": 0.03773809990686935 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.30057803468208094, "acc_stderr": 0.03496101481191181, "acc_norm": 0.30057803468208094, "acc_norm_stderr": 0.03496101481191181 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179962, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179962 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2978723404255319, "acc_stderr": 0.029896145682095455, "acc_norm": 0.2978723404255319, "acc_norm_stderr": 0.029896145682095455 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813344, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813344 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2689655172413793, "acc_stderr": 0.03695183311650232, "acc_norm": 0.2689655172413793, "acc_norm_stderr": 0.03695183311650232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.23809523809523808, "acc_stderr": 0.021935878081184756, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.021935878081184756 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574925, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574925 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.24838709677419354, "acc_stderr": 0.024580028921481003, "acc_norm": 0.24838709677419354, "acc_norm_stderr": 0.024580028921481003 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.21674876847290642, "acc_stderr": 0.028990331252516235, "acc_norm": 0.21674876847290642, "acc_norm_stderr": 0.028990331252516235 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3090909090909091, "acc_stderr": 0.036085410115739666, "acc_norm": 0.3090909090909091, "acc_norm_stderr": 0.036085410115739666 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2777777777777778, "acc_stderr": 0.03191178226713548, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03191178226713548 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.21243523316062177, "acc_stderr": 0.029519282616817258, "acc_norm": 0.21243523316062177, "acc_norm_stderr": 0.029519282616817258 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.34102564102564104, "acc_stderr": 0.02403548967633507, "acc_norm": 0.34102564102564104, "acc_norm_stderr": 0.02403548967633507 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2518518518518518, "acc_stderr": 0.02646611753895991, "acc_norm": 0.2518518518518518, "acc_norm_stderr": 0.02646611753895991 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.2310
