OALL/details_llm-mle__arb_mle_pretrained_8b
收藏Hugging Face2024-06-26 更新2024-06-29 收录
下载链接:
https://hf-mirror.com/datasets/OALL/details_llm-mle__arb_mle_pretrained_8b
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在模型 llm-mle/arb_mle_pretrained_8b 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2次运行中生成的,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳命名。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 的 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 llm-mle/arb_mle_pretrained_8b. The dataset is composed of 136 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from 2 runs, with each run represented as a specific split in each configuration, the split being 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
数据集来源
- 数据集自动创建于模型llm-mle/arb_mle_pretrained_8b的评估运行过程中。
数据集结构
- 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2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。
- 额外配置"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_llm-mle__arb_mle_pretrained_8b", "lighteval_xstory_cloze_ar_0", split="train")
最新结果
- 最新结果来自2024-06-26T17:05:58.628263的运行。
- 结果包括多个任务的准确率(acc_norm)和标准误差(acc_norm_stderr)。 python { "all": { "acc_norm": 0.6060012955675836, "acc_norm_stderr": 0.032342066915637006, "acc": 0.6512243547319656, "acc_stderr": 0.012264502012981186 }, "community|acva:Algeria|0": { "acc_norm": 0.8769230769230769, "acc_norm_stderr": 0.02358675520383352 }, "community|acva:Ancient_Egypt|0": { "acc_norm": 0.7936507936507936, "acc_norm_stderr": 0.02283764431923266 }, "community|acva:Arab_Empire|0": { "acc_norm": 0.8981132075471698, "acc_norm_stderr": 0.018617549758276685 }, "community|acva:Arabic_Architecture|0": { "acc_norm": 0.7743589743589744, "acc_norm_stderr": 0.030010921825357008 }, "community|acva:Arabic_Art|0": { "acc_norm": 0.7282051282051282, "acc_norm_stderr": 0.03194086187025724 }, "community|acva:Arabic_Astronomy|0": { "acc_norm": 0.5282051282051282, "acc_norm_stderr": 0.035840746749208334 }, "community|acva:Arabic_Calligraphy|0": { "acc_norm": 0.9058823529411765, "acc_norm_stderr": 0.018321227691875275 }, "community|acva:Arabic_Ceremony|0": { "acc_norm": 0.8108108108108109, "acc_norm_stderr": 0.0288734720923751 }, "community|acva:Arabic_Clothing|0": { "acc_norm": 0.8, "acc_norm_stderr": 0.028718326344709492 }, "community|acva:Arabic_Culture|0": { "acc_norm": 0.9538461538461539, "acc_norm_stderr": 0.01506406741240326 }, "community|acva:Arabic_Food|0": { "acc_norm": 0.8564102564102564, "acc_norm_stderr": 0.025176872172688033 }, "community|acva:Arabic_Funeral|0": { "acc_norm": 0.9052631578947369, "acc_norm_stderr": 0.030205285724061382 }, "community|acva:Arabic_Geography|0": { "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.03455930201924812 }, "community|acva:Arabic_History|0": { "acc_norm": 0.8769230769230769, "acc_norm_stderr": 0.02358675520383351 }, "community|acva:Arabic_Language_Origin|0": { "acc_norm": 0.8631578947368421, "acc_norm_stderr": 0.035447945577163416 }, "community|acva:Arabic_Literature|0": { "acc_norm": 0.9241379310344827, "acc_norm_stderr": 0.022064774506267183 }, "community|acva:Arabic_Math|0": { "acc_norm": 0.8051282051282052, "acc_norm_stderr": 0.02843846480726447 }, "community|acva:Arabic_Medicine|0": { "acc_norm": 0.9172413793103448, "acc_norm_stderr": 0.022959752132687576 }, "community|acva:Arabic_Music|0": { "acc_norm": 0.7410071942446043, "acc_norm_stderr": 0.03729198658164231 }, "community|acva:Arabic_Ornament|0": { "acc_norm": 0.9538461538461539, "acc_norm_stderr": 0.01506406741240328 }, "community|acva:Arabic_Philosophy|0": { "acc_norm": 0.9655172413793104, "acc_norm_stderr": 0.015205467304968908 }, "community|acva:Arabic_Physics_and_Chemistry|0": { "acc_norm": 0.9179487179487179, "acc_norm_stderr": 0.019703847178511633 }, "community|acva:Arabic_Wedding|0": { "acc_norm": 0.8974358974358975, "acc_norm_stderr": 0.021782039729793992 }, "community|acva:Bahrain|0": { "acc_norm": 0.8444444444444444, "acc_norm_stderr": 0.054638902368882934 }, "community|acva:Comoros|0": { "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.051247074319053836 }, "community|acva:Egypt_modern|0": { "acc_norm": 0.8631578947368421, "acc_norm_stderr": 0.035447945577163416 }, "community|acva:InfluenceFromAncientEgypt|0": { "acc_norm": 0.8769230769230769, "acc_norm_stderr": 0.023586755203833513 }, "community|acva:InfluenceFromByzantium|0": { "acc_norm": 0.9379310344827586, "acc_norm_stderr": 0.020106730671880315 }, "community|acva:InfluenceFromChina|0": { "acc_norm": 0.8102564102564103, "acc_norm_stderr": 0.0281510066376941 }, "community|acva:InfluenceFromGreece|0": { "acc_norm": 0.7487179487179487, "acc_norm_stderr": 0.031141461571214373 }, "community|acva:InfluenceFromIslam|0": { "acc_norm": 0.9310344827586207, "acc_norm_stderr": 0.021116290886061904 }, "community|acva:InfluenceFromPersia|0": { "acc_norm": 0.9314285714285714, "acc_norm_stderr": 0.019158952133882527 }, "community|acva:InfluenceFromRome|0": { "acc_norm": 0.7948717948717948, "acc_norm_stderr": 0.028990811252138902 }, "community|acva:Iraq|0": { "acc_norm": 0.8235294117647058, "acc_norm_stderr": 0.041594516540385144 }, "community|acva:Islam_Education|0": { "acc_norm": 0.8871794871794871, "acc_norm_stderr": 0.02271427689319132 }, "community|acva:Islam_branches_and_schools|0": { "acc_norm": 0.7428571428571429, "acc_norm_stderr": 0.033133343292217204 }, "community|acva:Islamic_law_system|0": { "acc_norm": 0.9230769230769231, "acc_norm_stderr": 0.019131384745146446 }, "community|acva:Jordan|0": { "acc_norm": 0.8, "acc_norm_stderr": 0.06030226891555273 }, "community|acva:Kuwait|0": { "acc_norm": 0.9333333333333333, "acc_norm_stderr": 0.03760507165451774 }, "community|acva:Lebanon|0": { "acc_norm": 0.8888888888888888, "acc_norm_stderr": 0.04737793696791344 }, "community|acva:Libya|0": { "acc_norm": 0.8, "acc_norm_stderr": 0.06030226891555273 }, "community|acva:Mauritania|0": { "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.05124707431905384 }, "community|acva:Mesopotamia_civilization|0": { "acc_norm": 0.8129032258064516, "acc_norm_stderr": 0.03142622480848988 }, "community|acva:Morocco|0": { "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.06478835438717 }, "community|acva:Oman|0": { "acc_norm": 0.9555555555555556, "acc_norm_stderr": 0.03106779090753475 }, "community|acva:Palestine|0": { "acc_norm": 0.788235294117647, "acc_norm_stderr": 0.04457743599957928 }, "community|acva:Qatar|0": { "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.05124707431905382 }, "community|acva:Saudi_Arabia|0": { "acc_norm": 0.9179487179487179, "acc_norm_stderr": 0.019703847178511626 }, "community|acva:Somalia|0": { "acc_norm": 0.8222222222222222, "acc_norm_stderr": 0.05763774795025094 }, "community|acva:Sudan|0": { "acc_norm": 0



