open-llm-leaderboard-old/details_cloudyu__mistral_18B_v0.1

Name: open-llm-leaderboard-old/details_cloudyu__mistral_18B_v0.1
Creator: open-llm-leaderboard-old
Published: 2024-03-05 19:09:12
License: 暂无描述

Hugging Face2024-03-05 更新2024-06-22 收录

下载链接：

https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_cloudyu__mistral_18B_v0.1

下载链接

链接失效反馈

官方服务：

资源简介：

数据集`Evaluation run of cloudyu/mistral_18B_v0.1`是在模型`cloudyu/mistral_18B_v0.1`的评估运行过程中自动生成的，评估运行是在`Open LLM Leaderboard`上进行的。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。此外，数据集还包含一个名为`results`的配置，用于存储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

数据集名称

名称: Evaluation run of cloudyu/mistral_18B_v0.1

数据集描述

描述: 该数据集是在评估模型 cloudyu/mistral_18B_v0.1 在 Open LLM Leaderboard 上的自动创建的。

数据集组成

组成: 数据集包含63个配置，每个配置对应一个评估任务。
创建: 数据集从1次运行中创建。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。
结果配置: 额外的 "results" 配置存储所有运行的聚合结果，用于计算并在 Open LLM Leaderboard 上显示聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cloudyu__mistral_18B_v0.1", "harness_winogrande_5", split="train")

配置详情

配置名称: harness_arc_challenge_25
- 数据文件:
  - 分割: 2024_03_05T19_06_24.770780
    - 路径: **/details_harness|arc:challenge|25_2024-03-05T19-06-24.770780.parquet
  - 分割: latest
    - 路径: **/details_harness|arc:challenge|25_2024-03-05T19-06-24.770780.parquet
配置名称: harness_gsm8k_5
- 数据文件:
  - 分割: 2024_03_05T19_06_24.770780
    - 路径: **/details_harness|gsm8k|5_2024-03-05T19-06-24.770780.parquet
  - 分割: latest
    - 路径: **/details_harness|gsm8k|5_2024-03-05T19-06-24.770780.parquet
配置名称: harness_hellaswag_10
- 数据文件:
  - 分割: 2024_03_05T19_06_24.770780
    - 路径: **/details_harness|hellaswag|10_2024-03-05T19-06-24.770780.parquet
  - 分割: latest
    - 路径: **/details_harness|hellaswag|10_2024-03-05T19-06-24.770780.parquet
配置名称: harness_hendrycksTest_5
- 数据文件:
  - 分割: 2024_03_05T19_06_24.770780
    - 路径:
      - **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-anatomy|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-astronomy|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-business_ethics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_biology|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_chemistry|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_computer_science|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_mathematics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_medicine|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-college_physics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-computer_security|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-econometrics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-formal_logic|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-global_facts|5_2024-03-05T19-06-24.770780.parquet
      - **/details_harness|hendrycksTest-high_school_biology|5_2024-03-05T19-06-24.770780.parquet