open-llm-leaderboard-old/details_AA051611__A0113
收藏数据集概述
该数据集是在模型 AA051611/A0113 的评估运行期间自动创建的，用于 Open LLM Leaderboard。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
数据集由多个配置组成，每个配置对应一个评估任务。每个配置包含多个运行结果，每个运行结果以时间戳命名的 split 形式存储。"train" split 始终指向最新的结果。
加载数据集
可以使用以下代码加载特定运行的详细信息：
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_AA051611__A0113", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-14T19:22:00.115237 运行 的最新结果：
python { "all": { "acc": 0.7396629430618338, "acc_stderr": 0.02895723757690259, "acc_norm": 0.7443509721070339, "acc_norm_stderr": 0.02950325667268791, "mc1": 0.412484700122399, "mc1_stderr": 0.01723329939957122, "mc2": 0.5965256915069256, "mc2_stderr": 0.01518941143132932 }, "harness|arc:challenge|25": { "acc": 0.6313993174061433, "acc_stderr": 0.014097810678042194, "acc_norm": 0.6638225255972696, "acc_norm_stderr": 0.013804855026205761 }, "harness|hellaswag|10": { "acc": 0.6549492133041227, "acc_stderr": 0.00474413282539152, "acc_norm": 0.848635729934276, "acc_norm_stderr": 0.0035767110656195833 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7111111111111111, "acc_stderr": 0.03915450630414251, "acc_norm": 0.7111111111111111, "acc_norm_stderr": 0.03915450630414251 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8552631578947368, "acc_stderr": 0.028631951845930387, "acc_norm": 0.8552631578947368, "acc_norm_stderr": 0.028631951845930387 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909284, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.8, "acc_stderr": 0.02461829819586651, "acc_norm": 0.8, "acc_norm_stderr": 0.02461829819586651 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.03167473383795718, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.03167473383795718 }, "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": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.03533133389323657, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.03533133389323657 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5, "acc_stderr": 0.04975185951049946, "acc_norm": 0.5, "acc_norm_stderr": 0.04975185951049946 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7659574468085106, "acc_stderr": 0.027678452578212383, "acc_norm": 0.7659574468085106, "acc_norm_stderr": 0.027678452578212383 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5877192982456141, "acc_stderr": 0.04630653203366596, "acc_norm": 0.5877192982456141, "acc_norm_stderr": 0.04630653203366596 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7241379310344828, "acc_stderr": 0.03724563619774632, "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.03724563619774632 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6428571428571429, "acc_stderr": 0.024677862841332783, "acc_norm": 0.6428571428571429, "acc_norm_stderr": 0.024677862841332783 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04444444444444449, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.867741935483871, "acc_stderr": 0.019272015434846478, "acc_norm": 0.867741935483871, "acc_norm_stderr": 0.019272015434846478 }, "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": 0.8, "acc_stderr": 0.040201512610368445, "acc_norm": 0.8, "acc_norm_stderr": 0.040201512610368445 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.028450388805284357, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.028450388805284357 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8888888888888888, "acc_stderr": 0.022390787638216773, "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.022390787638216773 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9533678756476683, "acc_stderr": 0.01521676181926258, "acc_norm": 0.9533678756476683, "acc_norm_stderr": 0.01521676181926258 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7923076923076923, "acc_stderr": 0.020567539567246784, "acc_norm": 0.7923076923076923, "acc_norm_stderr": 0.020567539567246784 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4111111111111111, "acc_stderr": 0.029999923508706682, "acc_norm": 0.4111111111111111, "acc_norm_stderr": 0.029999923508706682 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.8613445378151261, "acc_stderr": 0.022448264476832583, "acc_norm": 0.861344
