five

open-llm-leaderboard/details_microsoft__DialoGPT-medium

收藏
Hugging Face2023-12-03 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_microsoft__DialoGPT-medium
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microsoft/DialoGPT-medium时自动创建的,包含64个配置,每个配置对应一个评估任务。数据集由3次运行生成,每次运行的结果作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,还有一个名为results的配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。

This dataset was automatically created during the evaluation of the microsoft/DialoGPT-medium model, and includes 64 configurations, each corresponding to one evaluation task. The dataset is generated from three runs, with the results of each run serving as a data split under a specific configuration, and the split names are taken from the timestamp of the corresponding run. The train split always points to the most recent results. Furthermore, there is a configuration named `results` that stores the aggregated results of all runs, which is used to calculate and display aggregate metrics on the Open LLM Leaderboard.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集名称

  • Evaluation run of microsoft/DialoGPT-medium

数据集组成

  • 该数据集包含64个配置,每个配置对应一个评估任务。
  • 数据集从3次运行中创建,每次运行的时间戳作为特定分割的名称。
  • "train"分割始终指向最新的结果。

数据文件结构

  • 每个配置包含多个分割,每个分割对应一个特定的时间戳。
  • 最新的结果存储在名为"latest"的分割中。

示例代码

  • 加载特定运行的详细信息示例: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_microsoft__DialoGPT-medium", "harness_gsm8k_5", split="train")

最新结果

  • 最新结果来自2023-12-03T18:15:54.629306运行,示例如下: python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T19:21:27.633576.parquet
  • harness_drop_3

    • 分割:2023_10_18T05_52_00.103585, latest
    • 路径:**/details_harness|drop|3_2023-10-18T05-52-00.103585.parquet
  • harness_gsm8k_5

    • 分割:2023_10_18T05_52_00.103585, 2023_12_03T18_15_54.629306, latest
    • 路径:**/details_harness|gsm8k|5_2023-10-18T05-52-00.103585.parquet, **/details_harness|gsm8k|5_2023-12-03T18-15-54.629306.parquet
  • harness_hellaswag_10

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hellaswag|10_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:多个文件路径,例如**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T19:21:27.633576.parquet
  • harness_hendrycksTest_formal_logic_5

    • 分割:2023_07_19T19_21_27.633576, latest
    • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-07-19T19:21:27.633576.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