OALL/details_ibivibiv__multimaster-7b-v6
收藏数据集概述
数据集基本信息
- 名称: Evaluation run of ibivibiv/multimaster-7b-v6
- 来源: 自动创建于模型评估运行期间
- 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: 始终指向最新的结果
- 结果配置: 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_ibivibiv__multimaster-7b-v6", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
- 时间戳: 2024-06-18T21:51:08.718042
- 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: 0.5846153846153846
- acc_norm_stderr: 0.03538013280575029
-
任务: community|acva:Ancient_Egypt|0
- acc_norm: 0.6793650793650794
- acc_norm_stderr: 0.02633857021981403
-
任务: community|acva:Arab_Empire|0
- acc_norm: 0.4528301886792453
- acc_norm_stderr: 0.030635627957961823
-
任务: community|acva:Arabic_Architecture|0
- acc_norm: 0.6564102564102564
- acc_norm_stderr: 0.03409627301409854
-
任务: community|acva:Arabic_Art|0
- acc_norm: 0.5692307692307692
- acc_norm_stderr: 0.03555213252058761
-
任务: community|acva:Arabic_Astronomy|0
- acc_norm: 0.48717948717948717
- acc_norm_stderr: 0.03588610523192216
-
任务: community|acva:Arabic_Calligraphy|0
- acc_norm: 0.6313725490196078
- acc_norm_stderr: 0.030270516135386928
-
任务: community|acva:Arabic_Ceremony|0
- acc_norm: 0.6918918918918919
- acc_norm_stderr: 0.03403782277834384
-
任务: community|acva:Arabic_Clothing|0
- acc_norm: 0.49230769230769234
- acc_norm_stderr: 0.03589365940635213
-
任务: community|acva:Arabic_Culture|0
- acc_norm: 0.6717948717948717
- acc_norm_stderr: 0.03371243782413708
-
任务: community|acva:Arabic_Food|0
- acc_norm: 0.6564102564102564
- acc_norm_stderr: 0.03409627301409856
-
任务: community|acva:Arabic_Funeral|0
- acc_norm: 0.7894736842105263
- acc_norm_stderr: 0.04204923483878739
-
任务: community|acva:Arabic_Geography|0
- acc_norm: 0.6137931034482759
- acc_norm_stderr: 0.04057324734419035
-
任务: community|acva:Arabic_History|0
- acc_norm: 0.558974358974359
- acc_norm_stderr: 0.0356473293185358
-
任务: community|acva:Arabic_Language_Origin|0
- acc_norm: 0.7263157894736842
- acc_norm_stderr: 0.04598579376319263
-
任务: community|acva:Arabic_Literature|0
- acc_norm: 0.7379310344827587
- acc_norm_stderr: 0.03664666337225257
-
任务: community|acva:Arabic_Math|0
- acc_norm: 0.35384615384615387
- acc_norm_stderr: 0.03433004254147036
-
任务: community|acva:Arabic_Medicine|0
- acc_norm: 0.6758620689655173
- acc_norm_stderr: 0.03900432069185553
-
任务: community|acva:Arabic_Music|0
- acc_norm: 0.7050359712230215
- acc_norm_stderr: 0.03881956126735706
-
任务: community|acva:Arabic_Ornament|0
- acc_norm: 0.8051282051282052
- acc_norm_stderr: 0.028438464807264478
-
任务: community|acva:Arabic_Philosophy|0
- acc_norm: 0.8137931034482758
- acc_norm_stderr: 0.03243946159004616
-
任务: community|acva:Arabic_Physics_and_Chemistry|0
- acc_norm: 0.6358974358974359
- acc_norm_stderr: 0.03454653867786389
-
任务: community|acva:Arabic_Wedding|0
- acc_norm: 0.5897435897435898
- acc_norm_stderr: 0.03531493712326672
-
任务: community|acva:Bahrain|0
- acc_norm: 0.6444444444444445
- acc_norm_stderr: 0.07216392363431011
-
任务: community|acva:Comoros|0
- acc_norm: 0.5111111111111111
- acc_norm_stderr: 0.07535922203472523
-
任务: community|acva:Egypt_modern|0
- acc_norm: 0.5894736842105263
- acc_norm_stderr: 0.050738635645512085
-
任务: community|acva:InfluenceFromAncientEgypt|0
- acc_norm: 0.8153846153846154
- acc_norm_stderr: 0.02785571665575416
-
任务: community|acva:InfluenceFromByzantium|0
- acc_norm: 0.7517241379310344
- acc_norm_stderr: 0.03600105692727771
-
任务: community|acva:InfluenceFromChina|0
- acc_norm: 0.3128205128205128
- acc_norm_stderr: 0.03328755065724854
-
任务: community|acva:InfluenceFromGreece|0
- acc_norm: 0.7897435897435897
- acc_norm_stderr: 0.029256125643046835
-
任务: community|acva:InfluenceFromIslam|0
- acc_norm: 0.7862068965517242
- acc_norm_stderr: 0.03416520447747549
-
任务: community|acva:InfluenceFromPersia|0
- acc_norm: 0.8
- acc_norm_stderr: 0.030323921743156096
-
任务: community|acva:InfluenceFromRome|0
- acc_norm: 0.6666666666666666
- acc_norm_stderr: 0.033844872171120644
-
任务: community|acva:Iraq|0
- acc_norm: 0.7058823529411765
- acc_norm_stderr: 0.04971495616050099
-
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: 0.7085714285714285
- acc_norm_stderr: 0.03444952656229018
-
任务: community|acva:Islamic_law_system|0
- acc_norm: 0.6153846153846154
- acc_norm_stderr: 0.03492896993742303
-
任务: community|acva:Jordan|0
- acc_norm: 0.5333333333333333
- acc_norm_stderr: 0.0752101433090355
-
任务: community|acva:Kuwait|0
- acc_norm: 0.7333333333333333
- acc_norm_stderr: 0.06666666666666668
-
任务: community|acva:Lebanon|0
- acc_norm: 0.5555555555555556
- acc_norm_stderr: 0.07491109582924914
-
任务: community|acva:Libya|0
- acc_norm: 0.5777777777777777
- acc_norm_stderr: 0.07446027270295806
-
任务: community|acva:Mauritania|0
- acc_norm: 0.5555555555555556
- acc_norm_stderr: 0.07491109582924915
-
任务: community|acva:Mesopotamia_civilization|0
- acc_norm: 0.6645161290322581
- acc_norm_stderr: 0.03804768396523566
-
任务: community|acva:Morocco|0
- acc_norm: 0.7333333333333333
- acc_norm_stderr: 0.0666666666666667
-
任务: community|acva:Oman|0
- acc_norm: 0.7111111111111111
- acc_norm_stderr: 0.06832943242540508
-
任务: community|acva:Palestine|0
- acc_norm: 0.6352941176470588
- acc_norm_stderr: 0.052519327704200834
-
任务: community|acva:Qatar|0
- acc_norm: 0.7111111111111111
- acc_norm_stderr: 0.06832943242540508
-
任务: community|acva:Saudi_Arabia|0
- acc_norm: 0.6717948717948717
- acc_norm_stderr: 0.03371243782413707
-
任务: community|acva:Somalia|0
- acc_norm: 0.5555555555555556
- acc_norm_stderr: 0.07491109582924914
-
任务: community|acva:Sudan|0
- acc_norm: 0.6222222222222222
- acc_norm_stderr: 0.07309112127323451
-
任务: community|acva:Syria|0
- acc_norm: 0.7333333333333333
- acc_norm_stderr: 0.0666666666666667
-
任务: community|acva:Tunisia|0
- acc_norm: 0.5777777777777777
- acc_norm_stderr: 0.074460272



