five

open-llm-leaderboard-old/details_saishf__Top-Western-Maid-7B

收藏
Hugging Face2024-02-13 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_saishf__Top-Western-Maid-7B
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型saishf/Top-Western-Maid-7B进行评估时自动创建的。数据集由63个配置组成,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,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对模型saishf/Top-Western-Maid-7B进行评估时自动创建的。数据集由63个配置组成,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,分割以运行的时间戳命名。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型saishf/Top-Western-Maid-7BOpen LLM Leaderboard上的自动创建的。数据集包含63个配置,每个配置对应一个评估任务。

数据集结构

  • 配置数量:63个配置
  • 数据来源:从1次运行中创建,每个运行在每个配置中作为一个特定的分割存在,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。
  • 结果汇总:一个额外的配置"results"存储所有运行的汇总结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_saishf__Top-Western-Maid-7B", "harness_winogrande_5", split="train")

最新结果

以下是2024-02-13T11:07:35.441841运行的最新结果: python { "all": { "acc": 0.6506958953045886, "acc_stderr": 0.03211223802352257, "acc_norm": 0.6509594125199996, "acc_norm_stderr": 0.032774521752530913, "mc1": 0.42472460220318237, "mc1_stderr": 0.017304000957167477, "mc2": 0.5879284610844989, "mc2_stderr": 0.015340978033780782 }, "harness|arc:challenge|25": { "acc": 0.6638225255972696, "acc_stderr": 0.013804855026205763, "acc_norm": 0.6936860068259386, "acc_norm_stderr": 0.013470584417276513 }, "harness|hellaswag|10": { "acc": 0.6974706233817964, "acc_stderr": 0.004584144014654942, "acc_norm": 0.8740290778729337, "acc_norm_stderr": 0.003311384498158642 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.047609522856952365, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952365 }, ... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_02_13T11_07_35.441841
      • path: **/details_harness|arc:challenge|25_2024-02-13T11-07-35.441841.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-02-13T11-07-35.441841.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_02_13T11_07_35.441841
      • path: **/details_harness|gsm8k|5_2024-02-13T11-07-35.441841.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-02-13T11-07-35.441841.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_02_13T11_07_35.441841
      • path: **/details_harness|hellaswag|10_2024-02-13T11-07-35.441841.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-02-13T11-07-35.441841.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_02_13T11_07_35.441841
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-02-13T11-07-35.441841.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-02-13T11-07-35.441841.parquet ... }
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作