OALL/details_dfurman__Qwen2-72B-Orpo-v0.1
收藏数据集概述
数据集基本信息
- 名称: Evaluation run of dfurman/Qwen2-72B-Orpo-v0.1
- 来源: 自动创建于模型评估过程中
- 配置数量: 136
- 创建次数: 1次
数据集结构
- 配置: 每个配置对应一个评估任务
- 分割: 每个运行结果作为一个特定的分割,分割名称使用运行的时间戳
- 训练分割: 指向最新结果
- 结果配置: 存储所有运行的聚合结果
加载示例
python from datasets import load_dataset data = load_dataset("OALL/details_dfurman__Qwen2-72B-Orpo-v0.1", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
- 时间戳: 2024-07-19T00:12:40.550821
- 结果: 包含所有任务的评估结果,具体结果见链接
评估结果示例
json { "all": { "acc_norm": 0.6391783452486337, "acc_norm_stderr": 0.03651764927808481, "acc": 0.7028457974851092, "acc_stderr": 0.011760681560041963 }, "community|acva:Algeria|0": { "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03174930436412671 }, "community|acva:Ancient_Egypt|0": { "acc_norm": 0.35873015873015873, "acc_norm_stderr": 0.027066962960582367 }, "community|acva:Arab_Empire|0": { "acc_norm": 0.4, "acc_norm_stderr": 0.030151134457776292 }, "community|acva:Arabic_Architecture|0": { "acc_norm": 0.7282051282051282, "acc_norm_stderr": 0.031940861870257235 }, "community|acva:Arabic_Art|0": { "acc_norm": 0.3641025641025641, "acc_norm_stderr": 0.03454653867786389 }, "community|acva:Arabic_Astronomy|0": { "acc_norm": 0.5076923076923077, "acc_norm_stderr": 0.03589365940635213 }, "community|acva:Arabic_Calligraphy|0": { "acc_norm": 0.47843137254901963, "acc_norm_stderr": 0.0313435870640056 }, "community|acva:Arabic_Ceremony|0": { "acc_norm": 0.6756756756756757, "acc_norm_stderr": 0.03451039989562494 }, "community|acva:Arabic_Clothing|0": { "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.03397280032734095 }, "community|acva:Arabic_Culture|0": { "acc_norm": 0.7384615384615385, "acc_norm_stderr": 0.0315522880274276 }, "community|acva:Arabic_Food|0": { "acc_norm": 0.7128205128205128, "acc_norm_stderr": 0.03248373338539886 }, "community|acva:Arabic_Funeral|0": { "acc_norm": 0.5684210526315789, "acc_norm_stderr": 0.05108592673308947 }, "community|acva:Arabic_Geography|0": { "acc_norm": 0.7448275862068966, "acc_norm_stderr": 0.03632984052707842 }, "community|acva:Arabic_History|0": { "acc_norm": 0.5282051282051282, "acc_norm_stderr": 0.03584074674920833 }, "community|acva:Arabic_Language_Origin|0": { "acc_norm": 0.7263157894736842, "acc_norm_stderr": 0.045985793763192624 }, "community|acva:Arabic_Literature|0": { "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.03455930201924813 }, "community|acva:Arabic_Math|0": { "acc_norm": 0.4, "acc_norm_stderr": 0.035172622905632896 }, "community|acva:Arabic_Medicine|0": { "acc_norm": 0.6551724137931034, "acc_norm_stderr": 0.03960933549451207 }, "community|acva:Arabic_Music|0": { "acc_norm": 0.2446043165467626, "acc_norm_stderr": 0.03659146222520567 }, "community|acva:Arabic_Ornament|0": { "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.03357544396403132 }, "community|acva:Arabic_Philosophy|0": { "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.04043461861916747 }, "community|acva:Arabic_Physics_and_Chemistry|0": { "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.03265438393749512 }, "community|acva:Arabic_Wedding|0": { "acc_norm": 0.676923076923077, "acc_norm_stderr": 0.03357544396403133 }, "community|acva:Bahrain|0": { "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.07446027270295806 }, "community|acva:Comoros|0": { "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.0666666666666667 }, "community|acva:Egypt_modern|0": { "acc_norm": 0.6105263157894737, "acc_norm_stderr": 0.05029529117145395 }, "community|acva:InfluenceFromAncientEgypt|0": { "acc_norm": 0.6153846153846154, "acc_norm_stderr": 0.03492896993742303 }, "community|acva:InfluenceFromByzantium|0": { "acc_norm": 0.7241379310344828, "acc_norm_stderr": 0.03724563619774631 }, "community|acva:InfluenceFromChina|0": { "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.03313653039774172 }, "community|acva:InfluenceFromGreece|0": { "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.03265438393749511 }, "community|acva:InfluenceFromIslam|0": { "acc_norm": 0.8758620689655172, "acc_norm_stderr": 0.027478236983636627 }, "community|acva:InfluenceFromPersia|0": { "acc_norm": 0.8, "acc_norm_stderr": 0.030323921743156096 }, "community|acva:InfluenceFromRome|0": { "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.03433004254147036 }, "community|acva:Iraq|0": { "acc_norm": 0.6588235294117647, "acc_norm_stderr": 0.05172904297361928 }, "community|acva:Islam_Education|0": { "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.032654383937495125 }, "community|acva:Islam_branches_and_schools|0": { "acc_norm": 0.6342857142857142, "acc_norm_stderr": 0.036512267418799475 }, "community|acva:Islamic_law_system|0": { "acc_norm": 0.8205128205128205, "acc_norm_stderr": 0.027552343052171066 }, "community|acva:Jordan|0": { "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.07535922203472523 }, "community|acva:Kuwait|0": { "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.06979205927323111 }, "community|acva:Lebanon|0": { "acc_norm": 0.6888888888888889, "acc_norm_stderr": 0.06979205927323111 }, "community|acva:Libya|0": { "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.06267511942419626 }, "community|acva:Mauritania|0": { "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.07309112127323451 }, "community|acva:Mesopotamia_civilization|0": { "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.03466511701965932 }, "community|acva:Morocco|0": { "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.0666666666666667 }, "community|acva:Oman|0": { "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.06478835438717001 }, "community|acva:Palestine|0": { "acc_norm": 0.8, "acc_norm_stderr": 0.04364357804719844 }, "community|acva:Qatar|0": { "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.07446027270295806 }, "community|acva:Saudi_Arabia|0": { "acc_norm": 0.5487179487179488, "acc_norm_stderr": 0.035727098603183925 }, "community|acva:Somalia|0": { "acc_norm": 0.8444444444444444, "acc_norm_stderr": 0.05463890236888291 },



