OALL/details_oobabooga__CodeBooga-34B-v0.1
收藏数据集概述
数据集简介
- 名称: Evaluation run of oobabooga/CodeBooga-34B-v0.1
- 创建方式: 自动创建,用于评估模型 oobabooga/CodeBooga-34B-v0.1
- 组成: 包含136个配置,每个配置对应一个评估任务
- 创建次数: 从1次运行中创建,每次运行对应一个特定的分割(split),分割名称使用运行的时间戳
- 最新结果: "train" 分割始终指向最新结果
- 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_oobabooga__CodeBooga-34B-v0.1", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
- 时间戳: 2024-06-18T12:16:54.044163
- 结果: 包含多个任务的评估结果,具体结果如下:
任务结果示例
-
任务: community|acva:Algeria|0
- acc_norm: 0.6
- acc_norm_stderr: 0.035172622905632896
-
任务: community|acva:Ancient_Egypt|0
- acc_norm: 0.28888888888888886
- acc_norm_stderr: 0.0255781616375406
-
任务: community|acva:Arab_Empire|0
- acc_norm: 0.33962264150943394
- acc_norm_stderr: 0.029146904747798342
-
任务: community|acva:Arabic_Architecture|0
- acc_norm: 0.5384615384615384
- acc_norm_stderr: 0.03579154352544571
-
任务: community|acva:Arabic_Art|0
- acc_norm: 0.3487179487179487
- acc_norm_stderr: 0.034215338466705415
-
任务: community|acva:Arabic_Astronomy|0
- acc_norm: 0.4666666666666667
- acc_norm_stderr: 0.03581804596782233
-
任务: community|acva:Arabic_Calligraphy|0
- acc_norm: 0.5647058823529412
- acc_norm_stderr: 0.031108974626602746
-
任务: community|acva:Arabic_Ceremony|0
- acc_norm: 0.6054054054054054
- acc_norm_stderr: 0.0360321188626959
-
任务: community|acva:Arabic_Clothing|0
- acc_norm: 0.5333333333333333
- acc_norm_stderr: 0.03581804596782233
-
任务: community|acva:Arabic_Culture|0
- acc_norm: 0.5897435897435898
- acc_norm_stderr: 0.035314937123266714
-
任务: community|acva:Arabic_Food|0
- acc_norm: 0.6102564102564103
- acc_norm_stderr: 0.03501424776256371
-
任务: community|acva:Arabic_Funeral|0
- acc_norm: 0.4105263157894737
- acc_norm_stderr: 0.050738635645512106
-
任务: community|acva:Arabic_Geography|0
- acc_norm: 0.4413793103448276
- acc_norm_stderr: 0.04137931034482757
-
任务: community|acva:Arabic_History|0
- acc_norm: 0.3435897435897436
- acc_norm_stderr: 0.03409627301409855
-
任务: community|acva:Arabic_Language_Origin|0
- acc_norm: 0.6421052631578947
- acc_norm_stderr: 0.04944436957628254
-
任务: community|acva:Arabic_Literature|0
- acc_norm: 0.7655172413793103
- acc_norm_stderr: 0.035306258743465914
-
任务: community|acva:Arabic_Math|0
- acc_norm: 0.3128205128205128
- acc_norm_stderr: 0.03328755065724854
-
任务: community|acva:Arabic_Medicine|0
- acc_norm: 0.7172413793103448
- acc_norm_stderr: 0.03752833958003337
-
任务: community|acva:Arabic_Music|0
- acc_norm: 0.2517985611510791
- acc_norm_stderr: 0.03694846055443904
-
任务: community|acva:Arabic_Ornament|0
- acc_norm: 0.6153846153846154
- acc_norm_stderr: 0.03492896993742304
-
任务: community|acva:Arabic_Philosophy|0
- acc_norm: 0.4
- acc_norm_stderr: 0.04082482904638628
-
任务: community|acva:Arabic_Physics_and_Chemistry|0
- acc_norm: 0.6153846153846154
- acc_norm_stderr: 0.03492896993742304
-
任务: community|acva:Arabic_Wedding|0
- acc_norm: 0.7384615384615385
- acc_norm_stderr: 0.03155228802742761
-
任务: community|acva:Bahrain|0
- acc_norm: 0.4666666666666667
- acc_norm_stderr: 0.0752101433090355
-
任务: community|acva:Comoros|0
- acc_norm: 0.5333333333333333
- acc_norm_stderr: 0.0752101433090355
-
任务: community|acva:Egypt_modern|0
- acc_norm: 0.6631578947368421
- acc_norm_stderr: 0.04874810431502904
-
任务: community|acva:InfluenceFromAncientEgypt|0
- acc_norm: 0.7384615384615385
- acc_norm_stderr: 0.0315522880274276
-
任务: community|acva:InfluenceFromByzantium|0
- acc_norm: 0.5448275862068965
- acc_norm_stderr: 0.04149886942192117
-
任务: community|acva:InfluenceFromChina|0
- acc_norm: 0.5846153846153846
- acc_norm_stderr: 0.0353801328057503
-
任务: community|acva:InfluenceFromGreece|0
- acc_norm: 0.6
- acc_norm_stderr: 0.035172622905632896
-
任务: community|acva:InfluenceFromIslam|0
- acc_norm: 0.7310344827586207
- acc_norm_stderr: 0.036951833116502325
-
任务: community|acva:InfluenceFromPersia|0
- acc_norm: 0.8228571428571428
- acc_norm_stderr: 0.028943391569621366
-
任务: community|acva:InfluenceFromRome|0
- acc_norm: 0.5948717948717949
- acc_norm_stderr: 0.03524577495610961
-
任务: community|acva:Iraq|0
- acc_norm: 0.49411764705882355
- acc_norm_stderr: 0.05455069703232772
-
任务: community|acva:Islam_Education|0
- acc_norm: 0.6820512820512821
- acc_norm_stderr: 0.03343383454355787
-
任务: community|acva:Islam_branches_and_schools|0
- acc_norm: 0.52
- acc_norm_stderr: 0.03787456611791997
-
任务: community|acva:Islamic_law_system|0
- acc_norm: 0.6461538461538462
- acc_norm_stderr: 0.03433004254147036
-
任务: community|acva:Jordan|0
- acc_norm: 0.6
- acc_norm_stderr: 0.07385489458759965
-
任务: community|acva:Kuwait|0
- acc_norm: 0.4222222222222222
- acc_norm_stderr: 0.07446027270295806
-
任务: community|acva:Lebanon|0
- acc_norm: 0.6
- acc_norm_stderr: 0.07385489458759964
-
任务: community|acva:Libya|0
- acc_norm: 0.6666666666666666
- acc_norm_stderr: 0.07106690545187012
-
任务: community|acva:Mauritania|0
- acc_norm: 0.5777777777777777
- acc_norm_stderr: 0.07446027270295806
-
任务: community|acva:Mesopotamia_civilization|0
- acc_norm: 0.5225806451612903
- acc_norm_stderr: 0.0402500394824441
-
任务: community|acva:Morocco|0
- acc_norm: 0.7555555555555555
- acc_norm_stderr: 0.06478835438717
-
任务: community|acva:Oman|0
- acc_norm: 0.6
- acc_norm_stderr: 0.07385489458759965
-
任务: community|acva:Palestine|0
- acc_norm: 0.5411764705882353
- acc_norm_stderr: 0.0543691634273002
-
任务: community|acva:Qatar|0
- acc_norm: 0.4222222222222222
- acc_norm_stderr: 0.07446027270295806
-
任务: community|acva:Saudi_Arabia|0
- acc_norm: 0.676923076923077
- acc_norm_stderr: 0.03357544396403133
-
任务: community|acva:Somalia|0
- acc_norm: 0.6222222222222222
- acc_norm_stderr: 0.07309112127323451
-
任务: community|acva:Sudan|0
- acc_norm: 0.6
- acc_norm_stderr: 0.07385489458759965
-
任务: community|acva:Syria|0
- acc_norm: 0.6
- acc_norm_stderr: 0.07385489458759965
-
任务: community|acva:Tunisia|0
- acc_norm: 0.6666666666666666
- acc_norm_stderr: 0.07106690545187012
-
任务: community|acva:United_Arab_Emirates|0
- acc_norm: 0.6588235294117647
- acc_norm_stderr: 0.



