open-llm-leaderboard-old/details_TeeZee__GALAXY_v03_slimorca_1_epoch_50k
收藏数据集概述
数据集组成
该数据集包含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，每个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，用于计算和显示在Open LLM Leaderboard上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TeeZee__GALAXY_v03_slimorca_1_epoch_50k", "harness_winogrande_5", split="train")
最新结果
以下是最新结果的摘要：
python { "all": { "acc": 0.6429068488104553, "acc_stderr": 0.031568579426465154, "acc_norm": 0.6545451261957939, "acc_norm_stderr": 0.032434688884844555, "mc1": 0.3292533659730722, "mc1_stderr": 0.016451264440068235, "mc2": 0.4729775863182744, "mc2_stderr": 0.014526156575814261 }, "harness|arc:challenge|25": { "acc": 0.5989761092150171, "acc_stderr": 0.014322255790719867, "acc_norm": 0.6271331058020477, "acc_norm_stderr": 0.014131176760131169 }, "harness|hellaswag|10": { "acc": 0.6483768173670583, "acc_stderr": 0.004765012078929392, "acc_norm": 0.8458474407488548, "acc_norm_stderr": 0.0036035695286784127 }, "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": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.743421052631579, "acc_stderr": 0.0355418036802569, "acc_norm": 0.743421052631579, "acc_norm_stderr": 0.0355418036802569 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7018867924528301, "acc_stderr": 0.028152837942493857, "acc_norm": 0.7018867924528301, "acc_norm_stderr": 0.028152837942493857 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.035868792800803406, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.035868792800803406 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6242774566473989, "acc_stderr": 0.036928207672648664, "acc_norm": 0.6242774566473989, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3627450980392157, "acc_stderr": 0.047840607041056527, "acc_norm": 0.3627450980392157, "acc_norm_stderr": 0.047840607041056527 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5787234042553191, "acc_stderr": 0.03227834510146268, "acc_norm": 0.5787234042553191, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "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": 0.43386243386243384, "acc_stderr": 0.025525034382474887, "acc_norm": 0.43386243386243384, "acc_norm_stderr": 0.025525034382474887 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768177, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768177 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7774193548387097, "acc_stderr": 0.023664216671642518, "acc_norm": 0.7774193548387097, "acc_norm_stderr": 0.023664216671642518 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4630541871921182, "acc_stderr": 0.035083705204426656, "acc_norm": 0.4630541871921182, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8, "acc_stderr": 0.031234752377721175, "acc_norm": 0.8, "acc_norm_stderr": 0.031234752377721175 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8636363636363636, "acc_stderr": 0.024450155973189835, "acc_norm": 0.8636363636363636, "acc_norm_stderr": 0.024450155973189835 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.917098445595855, "acc_stderr": 0.01989934131572178, "acc_norm": 0.917098445595855, "acc_norm_stderr": 0.01989934131572178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6538461538461539, "acc_stderr": 0.024121125416941183, "acc_norm": 0.6538461538461539, "acc_norm_stderr": 0.024121125416941183 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4, "acc_stderr": 0.029869605095316904, "acc_norm": 0.4, "acc_norm_stderr": 0.029869605095316904 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6848739495798319, "acc_stderr": 0.03017680828897434, "acc_norm": 0.6848739495798319, "acc_norm_stderr": 0.03017680828897434 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.
