open-llm-leaderboard-old/details_TIGER-Lab__TIGERScore-13B
收藏数据集概述
数据集简介
该数据集是在对模型 TIGER-Lab/TIGERScore-13B 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
数据集组成
数据集包含 63 个配置，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_TIGER-Lab__TIGERScore-13B", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-05T03:14:38.151903 的运行： python { "all": { "acc": 0.5509288338439411, "acc_stderr": 0.03371533456595939, "acc_norm": 0.556027145751412, "acc_norm_stderr": 0.03441954318740276, "mc1": 0.2766217870257038, "mc1_stderr": 0.01565960575532692, "mc2": 0.4038156584139009, "mc2_stderr": 0.014621623321928684 }, "harness|arc:challenge|25": { "acc": 0.5469283276450512, "acc_stderr": 0.014546892052005628, "acc_norm": 0.590443686006826, "acc_norm_stderr": 0.01437035863247244 }, "harness|hellaswag|10": { "acc": 0.6377215694084843, "acc_stderr": 0.004796763521045228, "acc_norm": 0.8279227245568612, "acc_norm_stderr": 0.0037667619833193487 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5185185185185185, "acc_stderr": 0.043163785995113245, "acc_norm": 0.5185185185185185, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490437, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490437 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6, "acc_stderr": 0.030151134457776285, "acc_norm": 0.6, "acc_norm_stderr": 0.030151134457776285 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6041666666666666, "acc_stderr": 0.04089465449325582, "acc_norm": 0.6041666666666666, "acc_norm_stderr": 0.04089465449325582 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5375722543352601, "acc_stderr": 0.0380168510452446, "acc_norm": 0.5375722543352601, "acc_norm_stderr": 0.0380168510452446 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364396, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364396 }, "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": 0.4723404255319149, "acc_stderr": 0.03263597118409769, "acc_norm": 0.4723404255319149, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374767, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374767 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4689655172413793, "acc_stderr": 0.04158632762097828, "acc_norm": 0.4689655172413793, "acc_norm_stderr": 0.04158632762097828 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.0241804971643769, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.0241804971643769 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3492063492063492, "acc_stderr": 0.04263906892795132, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.04263906892795132 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6548387096774193, "acc_stderr": 0.02704574657353433, "acc_norm": 0.6548387096774193, "acc_norm_stderr": 0.02704574657353433 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3842364532019704, "acc_stderr": 0.03422398565657551, "acc_norm": 0.3842364532019704, "acc_norm_stderr": 0.03422398565657551 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6666666666666666, "acc_stderr": 0.0368105086916155, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.0368105086916155 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6818181818181818, "acc_stderr": 0.0331847733384533, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.0331847733384533 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8134715025906736, "acc_stderr": 0.02811209121011748, "acc_norm": 0.8134715025906736, "acc_norm_stderr": 0.02811209121011748 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5153846153846153, "acc_stderr": 0.02533900301010651, "acc_norm": 0.5153846153846153, "acc_norm_stderr": 0.02533900301010651 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.025928876132766104, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.025928876132766104 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.5840336134453782, "acc_stderr": 0.032016501007396114, "acc_norm": 0
