open-llm-leaderboard-old/details_ChaoticNeutrals__Bepis_9B

该数据集是在Open LLM Leaderboard上对模型ChaoticNeutrals/Bepis_9B进行评估时自动创建的。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行创建，每次运行可以在每个配置中找到特定的分割，分割以运行的时间戳命名。train分割始终指向最新的结果。此外，results配置存储了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。

原始信息汇总

数据集概述

数据集信息

• 名称: Evaluation run of ChaoticNeutrals/Bepis_9B
• 来源: 自动创建于模型 ChaoticNeutrals/Bepis_9B 在 Open LLM Leaderboard 的评估运行。

数据集组成

• 配置数量: 63
• 每个配置对应: 一个评估任务
• 创建次数: 1次
• 分割命名: 使用运行的时间戳
• "train"分割: 总是指向最新的结果
• 额外配置 "results": 存储所有运行的聚合结果，用于计算和显示聚合指标在 Open LLM Leaderboard。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ChaoticNeutrals__Bepis_9B", "harness_winogrande_5", split="train")

最新结果

• 最新结果来自: run 2024-03-04T07:04:07.439007
• 详细结果: 包含多个任务的准确率（acc）、标准化准确率（acc_norm）、误差（stderr）等指标。

配置信息

• 配置名称: harness_arc_challenge_25

  • 数据文件:
    • 分割: 2024_03_04T07_04_07.439007
      • 路径: **/details_harness|arc:challenge|25_2024-03-04T07-04-07.439007.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2024-03-04T07-04-07.439007.parquet

• 配置名称: harness_gsm8k_5

  • 数据文件:
    • 分割: 2024_03_04T07_04_07.439007
      • 路径: **/details_harness|gsm8k|5_2024-03-04T07-04-07.439007.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2024-03-04T07-04-07.439007.parquet

• 配置名称: harness_hellaswag_10

  • 数据文件:
    • 分割: 2024_03_04T07_04_07.439007
      • 路径: **/details_harness|hellaswag|10_2024-03-04T07-04-07.439007.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2024-03-04T07-04-07.439007.parquet

• 配置名称: harness_hendrycksTest_5

  • 数据文件:
    • 分割: 2024_03_04T07_04_07.439007
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2024-03-04T07-04-07.439007.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2024-03-04T07-04-07.439007.parquet