five

open-llm-leaderboard/details_ShenaoZ__0.001_ablation_5iters_bs256_iter_5

收藏
Hugging Face2024-04-23 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_ShenaoZ__0.001_ablation_5iters_bs256_iter_5
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ShenaoZ/0.001_ablation_5iters_bs256_iter_5的评估运行期间自动创建的,评估运行在Open LLM Leaderboard上进行。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。results配置存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在模型ShenaoZ/0.001_ablation_5iters_bs256_iter_5的评估运行期间自动创建的,评估运行在Open LLM Leaderboard上进行。数据集由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。results配置存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。
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 ShenaoZ/0.001_ablation_5iters_bs256_iter_5

创建目的: 该数据集是自动创建的,用于评估模型ShenaoZ/0.001_ablation_5iters_bs256_iter_5Open LLM Leaderboard上的表现。

数据集组成:

  • 配置数量: 63个
  • 每个配置对应一个评估任务
  • 数据来源: 1次运行
  • 数据分割: 每个配置中的数据按运行时间戳命名,"train"分割指向最新结果
  • 额外配置: "results",存储所有运行的聚合结果,用于计算和显示Leaderboard上的聚合指标

数据集加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ShenaoZ__0.001_ablation_5iters_bs256_iter_5", "harness_winogrande_5", split="train")

最新结果

最新结果来自run 2024-04-23T10:17:47.161136,包含多个任务的评估结果。

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_04_23T10_17_47.161136
        • path: **/details_harness|arc:challenge|25_2024-04-23T10-17-47.161136.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-04-23T10-17-47.161136.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_04_23T10_17_47.161136
        • path: **/details_harness|gsm8k|5_2024-04-23T10-17-47.161136.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-04-23T10-17-47.161136.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_04_23T10_17_47.161136
        • path: **/details_harness|hellaswag|10_2024-04-23T10-17-47.161136.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-04-23T10-17-47.161136.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_04_23T10_17_47.161136
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-04-23T10-17-47.161136.parquet
      • split: latest
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-04-23T10-17-47.161136.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-04-23T10-17-47.161136.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