OALL/details_cloudyu__Yi-34Bx2-MOE-200K

该数据集是在评估模型cloudyu/Yi-34Bx2-MOE-200K时自动创建的，包含136个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为一个特定的分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置，存储了所有运行的聚合结果。

原始信息汇总

数据集概述

数据集简介

• 名称: Evaluation run of cloudyu/Yi-34Bx2-MOE-200K
• 来源: 自动创建于模型评估过程中。
• 组成: 包含136个配置，每个配置对应一个评估任务。
• 创建方式: 从1次运行中生成，每次运行对应一个特定分割，分割名称使用运行的时间戳。
• 额外配置: 包含一个名为"results"的配置，存储所有运行的聚合结果。

数据加载示例

python from datasets import load_dataset data = load_dataset("OALL/details_cloudyu__Yi-34Bx2-MOE-200K", "lighteval_xstory_cloze_ar_0", split="train")

最新结果

• 时间戳: 2024-06-20T04:03:42.614737
• 结果: 包含多个任务的评估结果，具体包括acc_norm和acc_norm_stderr等指标。 python { "all": { "acc_norm": 0.4942879694954353, "acc_norm_stderr": 0.03763406847272182, "acc": 0.5731303772336201, "acc_stderr": 0.012728753181936876 }, "community|acva:Algeria|0": { "acc_norm": 0.5076923076923077, "acc_norm_stderr": 0.03589365940635213 }, "community|acva:Ancient_Egypt|0": { "acc_norm": 0.8285714285714286, "acc_norm_stderr": 0.02126873968208062 }, "community|acva:Arab_Empire|0": { "acc_norm": 0.49433962264150944, "acc_norm_stderr": 0.030770900763851302 }, "community|acva:Arabic_Architecture|0": { "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.0335754439640313 }, "community|acva:Arabic_Art|0": { "acc_norm": 0.5076923076923077, "acc_norm_stderr": 0.03589365940635213 }, "community|acva:Arabic_Astronomy|0": { "acc_norm": 0.48717948717948717, "acc_norm_stderr": 0.035886105231922164 }, "community|acva:Arabic_Calligraphy|0": { "acc_norm": 0.7764705882352941, "acc_norm_stderr": 0.02614044546554491 }, "community|acva:Arabic_Ceremony|0": { "acc_norm": 0.6432432432432432, "acc_norm_stderr": 0.035315455206482514 }, "community|acva:Arabic_Clothing|0": { "acc_norm": 0.6256410256410256, "acc_norm_stderr": 0.034746084306262345 }, "community|acva:Arabic_Culture|0": { "acc_norm": 0.7487179487179487, "acc_norm_stderr": 0.031141461571214366 }, "community|acva:Arabic_Food|0": { "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.03409627301409855 }, "community|acva:Arabic_Funeral|0": { "acc_norm": 0.43157894736842106, "acc_norm_stderr": 0.05108592673308946 }, "community|acva:Arabic_Geography|0": { "acc_norm": 0.6, "acc_norm_stderr": 0.04082482904638628 }, "community|acva:Arabic_History|0": { "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.03509545602262039 }, "community|acva:Arabic_Language_Origin|0": { "acc_norm": 0.7473684210526316, "acc_norm_stderr": 0.044817462433734835 }, "community|acva:Arabic_Literature|0": { "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.0394170763206489 }, "community|acva:Arabic_Math|0": { "acc_norm": 0.4205128205128205, "acc_norm_stderr": 0.03544138389303483 }, "community|acva:Arabic_Medicine|0": { "acc_norm": 0.6827586206896552, "acc_norm_stderr": 0.03878352372138622 }, "community|acva:Arabic_Music|0": { "acc_norm": 0.48201438848920863, "acc_norm_stderr": 0.04253528098920135 }, "community|acva:Arabic_Ornament|0": { "acc_norm": 0.6974358974358974, "acc_norm_stderr": 0.03298070870085619 }, "community|acva:Arabic_Philosophy|0": { "acc_norm": 0.6551724137931034, "acc_norm_stderr": 0.03960933549451208 }, "community|acva:Arabic_Physics_and_Chemistry|0": { "acc_norm": 0.7589743589743589, "acc_norm_stderr": 0.030707489381124213 }, "community|acva:Arabic_Wedding|0": { "acc_norm": 0.8512820512820513, "acc_norm_stderr": 0.025545685822858138 }, "community|acva:Bahrain|0": { "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.06979205927323111 }, "community|acva:Comoros|0": { "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.07446027270295806 }, "community|acva:Egypt_modern|0": { "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.04794350420740799 }, "community|acva:InfluenceFromAncientEgypt|0": { "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.03409627301409855 }, "community|acva:InfluenceFromByzantium|0": { "acc_norm": 0.8206896551724138, "acc_norm_stderr": 0.03196766433373187 }, "community|acva:InfluenceFromChina|0": { "acc_norm": 0.36923076923076925, "acc_norm_stderr": 0.03464841141863757 }, "community|acva:InfluenceFromGreece|0": { "acc_norm": 0.6820512820512821, "acc_norm_stderr": 0.03343383454355787 }, "community|acva:InfluenceFromIslam|0": { "acc_norm": 0.7862068965517242, "acc_norm_stderr": 0.034165204477475494 }, "community|acva:InfluenceFromPersia|0": { "acc_norm": 0.8628571428571429, "acc_norm_stderr": 0.026078428778822795 }, "community|acva:InfluenceFromRome|0": { "acc_norm": 0.5897435897435898, "acc_norm_stderr": 0.035314937123266714 }, "community|acva:Iraq|0": { "acc_norm": 0.6352941176470588, "acc_norm_stderr": 0.05251932770420082 }, "community|acva:Islam_Education|0": { "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.03357544396403132 }, "community|acva:Islam_branches_and_schools|0": { "acc_norm": 0.5542857142857143, "acc_norm_stderr": 0.037680833051447954 }, "community|acva:Islamic_law_system|0": { "acc_norm": 0.6923076923076923, "acc_norm_stderr": 0.033136530397741705 }, "community|acva:Jordan|0": { "acc_norm": 0.6, "acc_norm_stderr": 0.07385489458759965 }, "community|acva:Kuwait|0": { "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.06478835438717001 }, "community|acva:Lebanon|0": { "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.06666666666666668 }, "community|acva:Libya|0": { "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.07446027270295805 }, "community|acva:Mauritania|0": { "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.07535922203472523 }, "community|acva:Mesopotamia_civilization|0": { "acc_norm": 0.6064516129032258, "acc_norm_stderr": 0.039367404780577056 }, "community|acva:Morocco|0": { "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.07446027270295807 }, "community|acva:Oman|0": { "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.051247074319053836 }, "community|acva:Palestine|0": { "acc_norm": 0.49411764705882355, "acc_norm_stderr": 0.05455069703232772 }, "community|acva:Qatar|0": { "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.06666666666666668 }, "community|acva:Saudi_Arabia|0": { "acc_norm": 0.6, "acc_norm_stderr": 0.0351726229056329 }, "community|acva:Somalia|0": { "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.07309112127323451 }, "community|acva:Sudan|0": { "acc_norm": 0.6666666666666666, "acc_norm_stderr":