five

open-llm-leaderboard-old/details_ise-uiuc__Magicoder-S-DS-6.7B

收藏
Hugging Face2024-02-18 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_ise-uiuc__Magicoder-S-DS-6.7B
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ise-uiuc/Magicoder-S-DS-6.7B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的特定分割中找到,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ise-uiuc/Magicoder-S-DS-6.7B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的特定分割中找到,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

数据集来源

该数据集是在对模型 ise-uiuc/Magicoder-S-DS-6.7B 进行评估运行时自动创建的,评估结果展示在 Open LLM Leaderboard 上。

数据集组成

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

一个额外的配置 "results" 存储所有运行的聚合结果,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_ise-uiuc__Magicoder-S-DS-6.7B", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要: python { "all": { "acc": 0.38780471620669205, "acc_stderr": 0.03447012765513512, "acc_norm": 0.38975117234313966, "acc_norm_stderr": 0.03521064576477108, "mc1": 0.24969400244798043, "mc1_stderr": 0.015152286907148128, "mc2": 0.40995716482222777, "mc2_stderr": 0.014865347711727704 }, "harness|arc:challenge|25": { "acc": 0.35580204778157, "acc_stderr": 0.013990571137918755, "acc_norm": 0.38310580204778155, "acc_norm_stderr": 0.01420647266167288 }, "harness|hellaswag|10": { "acc": 0.41455885281816374, "acc_stderr": 0.004916388962142323, "acc_norm": 0.5448117904799841, "acc_norm_stderr": 0.004969701081068383 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, # 其他任务的结果... }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|gsm8k|5_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|hellaswag|10_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_02_18T13_01_09.679530
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-02-18T13-01-09.679530.parquet

        其他路径...

}

数据集配置

  • config_name: harness_arc_challenge_25

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|gsm8k|5_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_hellaswag_10

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|hellaswag|10_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2024_02_18T13_01_09.679530
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-02-18T13-01-09.679530.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-02-18T13-01-09.679530.parquet

        其他路径...

}

数据集配置

  • config_name: harness_arc_challenge_25

    • split: 2024_02_18T13_01_09.679530
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2024-02-18T13-01-09.679530.parquet
  • config_name: harness_gsm8k_5

    • split: 2024_02_18T13_01_0
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