open-llm-leaderboard-old/details_AA051610__A0106
收藏数据集概述
该数据集是在模型 AA051610/A0106 在 Open LLM Leaderboard 上的评估运行期间自动创建的。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 2 次运行创建，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_AA051610__A0106", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-07T23:07:28.080056 运行的最新结果：
python { "all": { "acc": 0.7368670822409534, "acc_stderr": 0.029070974182818815, "acc_norm": 0.7408880337597785, "acc_norm_stderr": 0.029626716433824633, "mc1": 0.3953488372093023, "mc1_stderr": 0.01711581563241819, "mc2": 0.5782373220428066, "mc2_stderr": 0.015253933341089682 }, "harness|arc:challenge|25": { "acc": 0.6416382252559727, "acc_stderr": 0.014012883334859859, "acc_norm": 0.6646757679180887, "acc_norm_stderr": 0.013796182947785562 }, "harness|hellaswag|10": { "acc": 0.6574387572196774, "acc_stderr": 0.004735962781136062, "acc_norm": 0.8505277833100976, "acc_norm_stderr": 0.003558246300379053 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7185185185185186, "acc_stderr": 0.038850042458002526, "acc_norm": 0.7185185185185186, "acc_norm_stderr": 0.038850042458002526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8421052631578947, "acc_stderr": 0.02967416752010147, "acc_norm": 0.8421052631578947, "acc_norm_stderr": 0.02967416752010147 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8113207547169812, "acc_stderr": 0.024079995130062253, "acc_norm": 0.8113207547169812, "acc_norm_stderr": 0.024079995130062253 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8333333333333334, "acc_stderr": 0.031164899666948617, "acc_norm": 0.8333333333333334, "acc_norm_stderr": 0.031164899666948617 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7052023121387283, "acc_stderr": 0.03476599607516478, "acc_norm": 0.7052023121387283, "acc_norm_stderr": 0.03476599607516478 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165044, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7702127659574468, "acc_stderr": 0.02750175294441242, "acc_norm": 0.7702127659574468, "acc_norm_stderr": 0.02750175294441242 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5350877192982456, "acc_stderr": 0.046920083813689104, "acc_norm": 0.5350877192982456, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7103448275862069, "acc_stderr": 0.03780019230438015, "acc_norm": 0.7103448275862069, "acc_norm_stderr": 0.03780019230438015 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6296296296296297, "acc_stderr": 0.02487081525105709, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.02487081525105709 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8709677419354839, "acc_stderr": 0.019070889254792747, "acc_norm": 0.8709677419354839, "acc_norm_stderr": 0.019070889254792747 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5812807881773399, "acc_stderr": 0.03471192860518468, "acc_norm": 0.5812807881773399, "acc_norm_stderr": 0.03471192860518468 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.78, "acc_stderr": 0.041633319989322605, "acc_norm": 0.78, "acc_norm_stderr": 0.041633319989322605 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8363636363636363, "acc_stderr": 0.02888787239548795, "acc_norm": 0.8363636363636363, "acc_norm_stderr": 0.02888787239548795 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9040404040404041, "acc_stderr": 0.020984808610047912, "acc_norm": 0.9040404040404041, "acc_norm_stderr": 0.020984808610047912 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9585492227979274, "acc_stderr": 0.014385432857476458, "acc_norm": 0.9585492227979274, "acc_norm_stderr": 0.014385432857476458 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8102564102564103, "acc_stderr": 0.019880165406588796, "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.019880165406588796 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02944316932303154, "acc_norm": 0.37037037037037035,
