five

open-llm-leaderboard-old/details_Undi95__CodeEngine

收藏
Hugging Face2023-10-25 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Undi95__CodeEngine
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Undi95/CodeEngine在Open LLM Leaderboard上的评估运行期间自动生成的。数据集由64个配置组成,每个配置对应一个被评估的任务。它由2次运行创建,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python代码加载数据集详细信息的示例,并包含了特定运行的最新结果。

该数据集是在模型Undi95/CodeEngine在Open LLM Leaderboard上的评估运行期间自动生成的。数据集由64个配置组成,每个配置对应一个被评估的任务。它由2次运行创建,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了如何使用Python代码加载数据集详细信息的示例,并包含了特定运行的最新结果。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 Undi95/CodeEngine 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

数据集结构

  • 数据集包含 64 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。
  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Undi95__CodeEngine", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-25T07:16:21.496689 运行 的最新结果: python { "all": { "em": 0.31008808724832215, "em_stderr": 0.004736734191590966, "f1": 0.4059154781879224, "f1_stderr": 0.004594505528583743, "acc": 0.38050967793280527, "acc_stderr": 0.00780116508471732 }, "harness|drop|3": { "em": 0.31008808724832215, "em_stderr": 0.004736734191590966, "f1": 0.4059154781879224, "f1_stderr": 0.004594505528583743 }, "harness|gsm8k|5": { "acc": 0.015163002274450341, "acc_stderr": 0.0033660229497263702 }, "harness|winogrande|5": { "acc": 0.7458563535911602, "acc_stderr": 0.012236307219708269 } }

配置详情

以下是数据集的配置详情:

  • harness_arc_challenge_25

    • 分割: 2023_09_12T11_51_31.235775
    • 路径: **/details_harness|arc:challenge|25_2023-09-12T11-51-31.235775.parquet
    • 分割: latest
    • 路径: **/details_harness|arc:challenge|25_2023-09-12T11-51-31.235775.parquet
  • harness_drop_3

    • 分割: 2023_10_25T07_16_21.496689
    • 路径: **/details_harness|drop|3_2023-10-25T07-16-21.496689.parquet
    • 分割: latest
    • 路径: **/details_harness|drop|3_2023-10-25T07-16-21.496689.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_25T07_16_21.496689
    • 路径: **/details_harness|gsm8k|5_2023-10-25T07-16-21.496689.parquet
    • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-10-25T07-16-21.496689.parquet
  • harness_hellaswag_10

    • 分割: 2023_09_12T11_51_31.235775
    • 路径: **/details_harness|hellaswag|10_2023-09-12T11-51-31.235775.parquet
    • 分割: latest
    • 路径: **/details_harness|hellaswag|10_2023-09-12T11-51-31.235775.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_09_12T11_51_31.235775
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-management|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-09-12T11-51-31.235775.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2023-0
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