five

open-llm-leaderboard-old/details_tuantran1632001__Psyfighter2-Orca2-13B-ties

收藏
Hugging Face2024-01-13 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_tuantran1632001__Psyfighter2-Orca2-13B-ties
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 [tuantran1632001/Psyfighter2-Orca2-13B-ties](https://huggingface.co/tuantran1632001/Psyfighter2-Orca2-13B-ties) 的评估运行期间自动创建的,评估运行在 [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) 上进行。数据集由63个配置组成,每个配置对应一个被评估的任务。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"存储了运行的所有聚合结果,并用于计算和显示 [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) 上的聚合指标。

该数据集是在模型 [tuantran1632001/Psyfighter2-Orca2-13B-ties](https://huggingface.co/tuantran1632001/Psyfighter2-Orca2-13B-ties) 的评估运行期间自动创建的,评估运行在 [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) 上进行。数据集由63个配置组成,每个配置对应一个被评估的任务。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"存储了运行的所有聚合结果,并用于计算和显示 [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/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tuantran1632001/Psyfighter2-Orca2-13B-tiesOpen LLM Leaderboard上的运行过程中自动创建的。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

数据集由1次运行创建,每个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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_tuantran1632001__Psyfighter2-Orca2-13B-ties", "harness_winogrande_5", split="train")

最新结果

以下是来自2024-01-13T15:05:15.491956运行的最新结果: python { "all": { "acc": 0.603383654987928, "acc_stderr": 0.03303267584618269, "acc_norm": 0.607142680047232, "acc_norm_stderr": 0.033700954867739115, "mc1": 0.39167686658506734, "mc1_stderr": 0.01708779588176963, "mc2": 0.5540489547722205, "mc2_stderr": 0.01582448369078134 }, "harness|arc:challenge|25": { "acc": 0.5878839590443686, "acc_stderr": 0.014383915302225403, "acc_norm": 0.6245733788395904, "acc_norm_stderr": 0.01415063143511173 }, "harness|hellaswag|10": { "acc": 0.6296554471220872, "acc_stderr": 0.00481910045686781, "acc_norm": 0.8173670583549094, "acc_norm_stderr": 0.0038557568514415437 }, "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

    • data_files:
      • split: 2024_01_13T15_05_15.491956
        • path: **/details_harness|arc:challenge|25_2024-01-13T15-05-15.491956.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-01-13T15-05-15.491956.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_01_13T15_05_15.491956
        • path: **/details_harness|gsm8k|5_2024-01-13T15-05-15.491956.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-01-13T15-05-15.491956.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_01_13T15_05_15.491956
        • path: **/details_harness|hellaswag|10_2024-01-13T15-05-15.491956.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-01-13T15-05-15.491956.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_01_13T15_05_15.491956
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-01-13T15-05-15.491956.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-01-13T15-05-15.491956.parquet

          其他文件路径...

}

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