OALL/details_upstage__SOLAR-10.7B-v1.0
收藏数据集概述
数据集简介
该数据集是在评估模型 upstage/SOLAR-10.7B-v1.0 的运行过程中自动创建的。
数据集组成
- 数据集包含 136 个配置，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建，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。
- 一个额外的配置 "results" 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_upstage__SOLAR-10.7B-v1.0", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
以下是 2024-05-20T19:19:45.765558 运行 的最新结果：
python { "all": { "acc_norm": 0.39157929067095903, "acc_norm_stderr": 0.037565793699945484, "acc": 0.5268034414295168, "acc_stderr": 0.012848623899505763 }, "community|acva:Algeria|0": { "acc_norm": 0.5743589743589743, "acc_norm_stderr": 0.03549871080367707 }, "community|acva:Ancient_Egypt|0": { "acc_norm": 0.20634920634920634, "acc_norm_stderr": 0.02283764431923266 }, "community|acva:Arab_Empire|0": { "acc_norm": 0.3320754716981132, "acc_norm_stderr": 0.028985455652334395 }, "community|acva:Arabic_Architecture|0": { "acc_norm": 0.517948717948718, "acc_norm_stderr": 0.035874770987738246 }, "community|acva:Arabic_Art|0": { "acc_norm": 0.40512820512820513, "acc_norm_stderr": 0.035245774956109616 }, "community|acva:Arabic_Astronomy|0": { "acc_norm": 0.49743589743589745, "acc_norm_stderr": 0.03589743589743588 }, "community|acva:Arabic_Calligraphy|0": { "acc_norm": 0.4823529411764706, "acc_norm_stderr": 0.031353244021767514 }, "community|acva:Arabic_Ceremony|0": { "acc_norm": 0.5405405405405406, "acc_norm_stderr": 0.03673912620649471 }, "community|acva:Arabic_Clothing|0": { "acc_norm": 0.558974358974359, "acc_norm_stderr": 0.03564732931853579 }, "community|acva:Arabic_Culture|0": { "acc_norm": 0.3076923076923077, "acc_norm_stderr": 0.03313653039774173 }, "community|acva:Arabic_Food|0": { "acc_norm": 0.5025641025641026, "acc_norm_stderr": 0.03589743589743589 }, "community|acva:Arabic_Funeral|0": { "acc_norm": 0.4105263157894737, "acc_norm_stderr": 0.05073863564551211 }, "community|acva:Arabic_Geography|0": { "acc_norm": 0.6, "acc_norm_stderr": 0.04082482904638628 }, "community|acva:Arabic_History|0": { "acc_norm": 0.40512820512820513, "acc_norm_stderr": 0.03524577495610961 }, "community|acva:Arabic_Language_Origin|0": { "acc_norm": 0.6526315789473685, "acc_norm_stderr": 0.049109474007766586 }, "community|acva:Arabic_Literature|0": { "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419034 }, "community|acva:Arabic_Math|0": { "acc_norm": 0.41025641025641024, "acc_norm_stderr": 0.0353149371232667 }, "community|acva:Arabic_Medicine|0": { "acc_norm": 0.6551724137931034, "acc_norm_stderr": 0.03960933549451208 }, "community|acva:Arabic_Music|0": { "acc_norm": 0.2302158273381295, "acc_norm_stderr": 0.03583542294357027 }, "community|acva:Arabic_Ornament|0": { "acc_norm": 0.4307692307692308, "acc_norm_stderr": 0.035552132520587615 }, "community|acva:Arabic_Philosophy|0": { "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "community|acva:Arabic_Physics_and_Chemistry|0": { "acc_norm": 0.5897435897435898, "acc_norm_stderr": 0.035314937123266714 }, "community|acva:Arabic_Wedding|0": { "acc_norm": 0.4256410256410256, "acc_norm_stderr": 0.03549871080367708 }, "community|acva:Bahrain|0": { "acc_norm": 0.35555555555555557, "acc_norm_stderr": 0.07216392363431012 }, "community|acva:Comoros|0": { "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.07491109582924915 }, "community|acva:Egypt_modern|0": { "acc_norm": 0.6526315789473685, "acc_norm_stderr": 0.04910947400776659 }, "community|acva:InfluenceFromAncientEgypt|0": { "acc_norm": 0.5487179487179488, "acc_norm_stderr": 0.035727098603183925 }, "community|acva:InfluenceFromByzantium|0": { "acc_norm": 0.6620689655172414, "acc_norm_stderr": 0.039417076320648906 }, "community|acva:InfluenceFromChina|0": { "acc_norm": 0.2512820512820513, "acc_norm_stderr": 0.031141461571214373 }, "community|acva:InfluenceFromGreece|0": { "acc_norm": 0.7487179487179487, "acc_norm_stderr": 0.03114146157121436 }, "community|acva:InfluenceFromIslam|0": { "acc_norm": 0.4206896551724138, "acc_norm_stderr": 0.0411391498118926 }, "community|acva:InfluenceFromPersia|0": { "acc_norm": 0.6971428571428572, "acc_norm_stderr": 0.03483414676585986 }, "community|acva:InfluenceFromRome|0": { "acc_norm": 0.5487179487179488, "acc_norm_stderr": 0.035727098603183925 }, "community|acva:Iraq|0": { "acc_norm": 0.5647058823529412, "acc_norm_stderr": 0.05409572080481032 }, "community|acva:Islam_Education|0": { "acc_norm": 0.49743589743589745, "acc_norm_stderr": 0.03589743589743588 }, "community|acva:Islam_branches_and_schools|0": { "acc_norm": 0.4514285714285714, "acc_norm_stderr": 0.037725628985298354 }, "community|acva:Islamic_law_system|0": { "acc_norm": 0.4256410256410256, "acc_norm_stderr": 0.035498710803677086 }, "community|acva:Jordan|0": { "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.07309112127323451 }, "community|acva:Kuwait|0": { "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.06666666666666667 }, "community|acva:Lebanon|0": { "acc_norm": 0.17777777777777778, "acc_norm_stderr": 0.05763774795025094 }, "community|acva:Libya|0": { "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.07491109582924914 }, "community|acva:Mauritania|0": { "acc_norm": 0.4888888888888889, "acc_norm_stderr": 0.07535922203472523 }, "community|acva:Mesopotamia_civilization|0": { "acc_norm": 0.6258064516129033, "acc_norm_stderr": 0.03899489949435862 }, "community|acva:Morocco|0": { "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.07309112127323451 }, "community|acva:Oman|0": { "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.07106690545187012 }, "community|acva:Palestine|0": { "acc_norm": 0.3058823529411765, "acc_norm_stderr": 0.05027523520585574 }, "community|acva:Qatar|0": { "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.0752101433090355 }, "community|acva:Saudi_Arabia|0": { "acc_norm": 0.3641025641025641, "acc_norm_stderr": 0.03454653867786388 }, "community|acva:Somalia|
