遇见数据集

OALL/details_GritLM__GritLM-7B-KTO

收藏
Hugging Face2024-06-15 更新2024-06-29 收录
官方服务:

资源简介:

该数据集是在模型GritLM/GritLM-7B-KTO的评估运行期间自动创建的。数据集由136个配置组成,每个配置对应一个评估任务。数据集是从1次运行中生成的,每次运行在每种配置中表示为特定的分割,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,名为results的配置存储了所有运行的聚合结果。README还提供了如何使用Hugging Face datasets库加载数据集的示例,并包含了特定运行的最新结果。

The dataset was automatically created during the evaluation run of the model GritLM/GritLM-7B-KTO. The dataset is composed of 136 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from 1 run, with each run represented as a specific split in each configuration, named using the timestamp of the run. The train split always points to the latest results. An additional configuration named results stores all the aggregated results of the run. The README also provides an example of how to load the dataset using the Hugging Face datasets library and includes the latest results from a specific run.

提供机构:
OALL
原始信息汇总

数据集概述

数据集基本信息

  • 名称: Evaluation run of GritLM/GritLM-7B-KTO
  • 创建方式: 自动创建于模型 GritLM/GritLM-7B-KTO 的评估运行过程中。
  • 配置数量: 136 个配置,每个配置对应一个评估任务。
  • 创建次数: 1 次运行,每个运行结果存储在特定的分割中,分割名称使用运行的时间戳。
  • 最新结果: "train" 分割始终指向最新的结果。
  • 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_GritLM__GritLM-7B-KTO", "lighteval_xstory_cloze_ar_0", split="train")

最新结果

  • 时间戳: 2024-06-15T00:12:51.590562
  • 结果: 包含多个任务的评估结果,具体结果如下:
    • 总体结果:
      • acc_norm: 0.37215988324272276
      • acc_norm_stderr: 0.03709306492938823
      • acc: 0.5208471211118465
      • acc_stderr: 0.012855936282881265
    • 具体任务结果:
      • community|acva:Algeria|0:
        • acc_norm: 0.5230769230769231
        • acc_norm_stderr: 0.0358596530894741
      • community|acva:Ancient_Egypt|0:
        • acc_norm: 0.050793650793650794
        • acc_norm_stderr: 0.01239139518482262
      • community|acva:Arab_Empire|0:
        • acc_norm: 0.3132075471698113
        • acc_norm_stderr: 0.02854479331905533
      • community|acva:Arabic_Architecture|0:
        • acc_norm: 0.4564102564102564
        • acc_norm_stderr: 0.035761230969912135
      • community|acva:Arabic_Art|0:
        • acc_norm: 0.38461538461538464
        • acc_norm_stderr: 0.03492896993742304
      • community|acva:Arabic_Astronomy|0:
        • acc_norm: 0.4666666666666667
        • acc_norm_stderr: 0.03581804596782233
      • community|acva:Arabic_Calligraphy|0:
        • acc_norm: 0.36470588235294116
        • acc_norm_stderr: 0.030202433919892052
      • community|acva:Arabic_Ceremony|0:
        • acc_norm: 0.518918918918919
        • acc_norm_stderr: 0.036834092970087065
      • community|acva:Arabic_Clothing|0:
        • acc_norm: 0.5128205128205128
        • acc_norm_stderr: 0.03588610523192215
      • community|acva:Arabic_Culture|0:
        • acc_norm: 0.2358974358974359
        • acc_norm_stderr: 0.030481516761721537
      • community|acva:Arabic_Food|0:
        • acc_norm: 0.441025641025641
        • acc_norm_stderr: 0.0356473293185358
      • community|acva:Arabic_Funeral|0:
        • acc_norm: 0.4
        • acc_norm_stderr: 0.050529115263991134
      • community|acva:Arabic_Geography|0:
        • acc_norm: 0.6137931034482759
        • acc_norm_stderr: 0.04057324734419036
      • community|acva:Arabic_History|0:
        • acc_norm: 0.30256410256410254
        • acc_norm_stderr: 0.03298070870085619
      • community|acva:Arabic_Language_Origin|0:
        • acc_norm: 0.5473684210526316
        • acc_norm_stderr: 0.051339113773544845
      • community|acva:Arabic_Literature|0:
        • acc_norm: 0.47586206896551725
        • acc_norm_stderr: 0.041618085035015295
      • community|acva:Arabic_Math|0:
        • acc_norm: 0.30256410256410254
        • acc_norm_stderr: 0.03298070870085618
      • community|acva:Arabic_Medicine|0:
        • acc_norm: 0.46206896551724136
        • acc_norm_stderr: 0.041546596717075474
      • community|acva:Arabic_Music|0:
        • acc_norm: 0.23741007194244604
        • acc_norm_stderr: 0.036220593237998276
      • community|acva:Arabic_Ornament|0:
        • acc_norm: 0.5076923076923077
        • acc_norm_stderr: 0.03589365940635213
      • community|acva:Arabic_Philosophy|0:
        • acc_norm: 0.5793103448275863
        • acc_norm_stderr: 0.0411391498118926
      • community|acva:Arabic_Physics_and_Chemistry|0:
        • acc_norm: 0.5333333333333333
        • acc_norm_stderr: 0.03581804596782232
      • community|acva:Arabic_Wedding|0:
        • acc_norm: 0.4205128205128205
        • acc_norm_stderr: 0.03544138389303483
      • community|acva:Bahrain|0:
        • acc_norm: 0.3111111111111111
        • acc_norm_stderr: 0.06979205927323111
      • community|acva:Comoros|0:
        • acc_norm: 0.37777777777777777
        • acc_norm_stderr: 0.07309112127323451
      • community|acva:Egypt_modern|0:
        • acc_norm: 0.3157894736842105
        • acc_norm_stderr: 0.04794350420740798
      • community|acva:InfluenceFromAncientEgypt|0:
        • acc_norm: 0.6051282051282051
        • acc_norm_stderr: 0.03509545602262038
      • community|acva:InfluenceFromByzantium|0:
        • acc_norm: 0.7172413793103448
        • acc_norm_stderr: 0.03752833958003337
      • community|acva:InfluenceFromChina|0:
        • acc_norm: 0.26666666666666666
        • acc_norm_stderr: 0.0317493043641267
      • community|acva:InfluenceFromGreece|0:
        • acc_norm: 0.6307692307692307
        • acc_norm_stderr: 0.034648411418637566
      • community|acva:InfluenceFromIslam|0:
        • acc_norm: 0.296551724137931
        • acc_norm_stderr: 0.03806142687309993
      • community|acva:InfluenceFromPersia|0:
        • acc_norm: 0.7028571428571428
        • acc_norm_stderr: 0.03464507889884372
      • community|acva:InfluenceFromRome|0:
        • acc_norm: 0.5743589743589743
        • acc_norm_stderr: 0.03549871080367708
      • community|acva:Iraq|0:
        • acc_norm: 0.5058823529411764
        • acc_norm_stderr: 0.05455069703232772
      • community|acva:Islam_Education|0:
        • acc_norm: 0.4512820512820513
        • acc_norm_stderr: 0.03572709860318392
      • community|acva:Islam_branches_and_schools|0:
        • acc_norm: 0.4685714285714286
        • acc_norm_stderr: 0.03782994654682182
      • community|acva:Islamic_law_system|0:
        • acc_norm: 0.4256410256410256
        • acc_norm_stderr: 0.035498710803677086
      • community|acva:Jordan|0:
        • acc_norm: 0.3333333333333333
        • acc_norm_stderr: 0.07106690545187012
      • 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: 0.4222222222222222
        • acc_norm_stderr: 0.07446027270295805
      • community|acva:Mesopotamia_civilization|0:
        • acc_norm: 0.5225806451612903
        • acc_norm_stderr: 0.0402500394824441
      • community|acva:Morocco|0:
        • acc_norm: 0.2222222222222222
        • acc_norm_stderr: 0.06267511942419628
      • community|acva:Oman|0:
        • acc_norm: 0.17777777777777778
        • acc_norm_stderr: 0.05763774795025094
      • community|acva:Palestine|0:
        • acc_norm: 0.24705882352941178
        • acc_norm_stderr: 0.047058823529411785
      • community|acva:Qatar|0:
        • acc_norm: 0.4222222222222222
        • acc_norm_stderr: 0.07446027270295806
      • community|acva:Saudi_Arabia|0:
        • acc_norm: 0.3282051282051282
        • acc_norm_stderr: 0.03371243782413707
      • community|acva:Somalia|0:
        • acc_norm: 0.35555555555555557
        • acc_norm_stderr: 0.07216392363431012
      • community|acva:Sudan|0:
        • acc_norm: 0.35555555555555557
        • acc_norm_stderr: 0.07216392363431012
      • `community
二维码
社区交流群
二维码
科研交流群
商业服务