five

open-llm-leaderboard-old/details_RESMPDEV__Qwen1.5-Wukong-0.5B

收藏
Hugging Face2024-02-19 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_RESMPDEV__Qwen1.5-Wukong-0.5B
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型RESMPDEV/Qwen1.5-Wukong-0.5B时自动创建的,包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定配置中的一个分割,分割名称使用运行的时间戳。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,用于计算和展示在Open LLM Leaderboard上的聚合指标。

该数据集是在评估模型RESMPDEV/Qwen1.5-Wukong-0.5B时自动创建的,包含63个配置,每个配置对应一个评估任务。数据集由1次运行生成,每次运行的结果存储为特定配置中的一个分割,分割名称使用运行的时间戳。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,用于计算和展示在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

数据集摘要

该数据集是在评估模型 RESMPDEV/Qwen1.5-Wukong-0.5BOpen 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_RESMPDEV__Qwen1.5-Wukong-0.5B", "harness_winogrande_5", split="train")

最新结果

这些是最新结果的示例,来自运行 2024-02-19T19:55:44.783229: python { "all": { "acc": 0.3817203865676145, "acc_stderr": 0.034089822227601395, "acc_norm": 0.3848469655600226, "acc_norm_stderr": 0.0348511286935856, "mc1": 0.2252141982864137, "mc1_stderr": 0.014623240768023496, "mc2": 0.38916482019581305, "mc2_stderr": 0.014419624366247177 }, "harness|arc:challenge|25": { "acc": 0.2790102389078498, "acc_stderr": 0.013106784883601353, "acc_norm": 0.3174061433447099, "acc_norm_stderr": 0.013602239088038169 }, "harness|hellaswag|10": { "acc": 0.3746265684126668, "acc_stderr": 0.004830371317841069, "acc_norm": 0.47779326827325236, "acc_norm_stderr": 0.004984857671187102 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_02_19T19_55_44.783229
        • **/details_harness|arc:challenge|25_2024-02-19T19-55-44.783229.parquet
      • split: latest
        • **/details_harness|arc:challenge|25_2024-02-19T19-55-44.783229.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_02_19T19_55_44.783229
        • **/details_harness|gsm8k|5_2024-02-19T19-55-44.783229.parquet
      • split: latest
        • **/details_harness|gsm8k|5_2024-02-19T19-55-44.783229.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_02_19T19_55_44.783229
        • **/details_harness|hellaswag|10_2024-02-19T19-55-44.783229.parquet
      • split: latest
        • **/details_harness|hellaswag|10_2024-02-19T19-55-44.783229.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_02_19T19_55_44.783229
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-international_law|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-management|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-marketing|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2024-02-19T19-55-44.783229.parquet
        • **/details_harness|hendrycksTest-professional_law|5_2024-02-19T19-55-44.783229.parquet
        • **/details_
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