open-llm-leaderboard-old/details_Xenon1__Zenith-7B-dpo-v1
收藏数据集概述
数据集名称
Evaluation run of Xenon1/Zenith-7B-dpo-v1
数据集描述
该数据集是在模型Xenon1/Zenith-7B-dpo-v1在Open LLM Leaderboard上的评估运行期间自动创建的。
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。数据集从2次运行中创建，每次运行可以在每个配置中找到一个特定的分割，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_Xenon1__Zenith-7B-dpo-v1", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2024-02-15T00:49:59.820976的运行（注意可能还有其他任务的结果，每个任务的最新结果可以在"results"和"latest"分割中找到）：
python { "all": { "acc": 0.5994007032450553, "acc_stderr": 0.03314392404148924, "acc_norm": 0.6077867814262741, "acc_norm_stderr": 0.033870966769135216, "mc1": 0.4357405140758874, "mc1_stderr": 0.017358345398863127, "mc2": 0.6059869573691794, "mc2_stderr": 0.015948076495091498 }, "harness|arc:challenge|25": { "acc": 0.5554607508532423, "acc_stderr": 0.014521226405627082, "acc_norm": 0.6049488054607508, "acc_norm_stderr": 0.014285898292938163 }, "harness|hellaswag|10": { "acc": 0.6405098585939056, "acc_stderr": 0.004788703173474748, "acc_norm": 0.8295160326628161, "acc_norm_stderr": 0.003752888662249574 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.631578947368421, "acc_stderr": 0.03925523381052932, "acc_norm": 0.631578947368421, "acc_norm_stderr": 0.03925523381052932 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.028544793319055326, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6597222222222222, "acc_stderr": 0.039621355734862175, "acc_norm": 0.6597222222222222, "acc_norm_stderr": 0.039621355734862175 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5549132947976878, "acc_stderr": 0.03789401760283647, "acc_norm": 0.5549132947976878, "acc_norm_stderr": 0.03789401760283647 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909281, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909281 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.04657047260594963, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.04657047260594963 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3968253968253968, "acc_stderr": 0.025197101074246494, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.025197101074246494 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.0442626668137991, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.0442626668137991 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7, "acc_stderr": 0.026069362295335137, "acc_norm": 0.7, "acc_norm_stderr": 0.026069362295335137 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7151515151515152, "acc_stderr": 0.03524390844511781, "acc_norm": 0.7151515151515152, "acc_norm_stderr": 0.03524390844511781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7929292929292929, "acc_stderr": 0.02886977846026704, "acc_norm": 0.7929292929292929, "acc_norm_stderr": 0.02886977846026704 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164525, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164525 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5871794871794872, "acc_stderr": 0.024962683564331796, "acc_norm": 0.5871794871794872, "acc_norm_stderr": 0.024962683564331796 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34814814814814815, "acc_stderr": 0.029045600290616265, "acc_norm": 0.34814814814814815, "acc_norm_stderr": 0.029045600290616265 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.634453781512605, "acc_stderr":
