five

open-llm-leaderboard-old/details_yleo__EmertonMonarch-7B-slerp

收藏
Hugging Face2024-02-14 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_yleo__EmertonMonarch-7B-slerp
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yleo/EmertonMonarch-7B-slerp在Open LLM Leaderboard上的评估运行过程中自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集由3次运行生成,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,还有一个名为results的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。

该数据集是在模型yleo/EmertonMonarch-7B-slerp在Open LLM Leaderboard上的评估运行过程中自动创建的。数据集由63个配置组成,每个配置对应一个被评估的任务。数据集由3次运行生成,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,还有一个名为results的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。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 yleo/EmertonMonarch-7B-slerpOpen LLM Leaderboard 上的自动创建的。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 3 次运行结果组成,每次运行的结果可以在每个配置中找到,并以运行的时间戳命名。"train" 分割始终指向最新的结果。此外,还有一个名为 "results" 的配置,存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

数据加载示例

以下是加载特定运行结果的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_yleo__EmertonMonarch-7B-slerp", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的摘要: python { "all": { "acc": 0.6501150387509795, "acc_stderr": 0.03215193957481397, "acc_norm": 0.6499843763084299, "acc_norm_stderr": 0.032817026545135845, "mc1": 0.6070991432068543, "mc1_stderr": 0.017097248285233065, "mc2": 0.765485798344535, "mc2_stderr": 0.013934106144304993 }, "harness|arc:challenge|25": { "acc": 0.7005119453924915, "acc_stderr": 0.013385021637313572, "acc_norm": 0.7303754266211604, "acc_norm_stderr": 0.012968040686869148 }, "harness|hellaswag|10": { "acc": 0.7105158334993029, "acc_stderr": 0.004525960965551706, "acc_norm": 0.8893646683927504, "acc_norm_stderr": 0.0031303894668332022 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, # 其他任务的结果... }

配置详情

数据集包含多个配置,每个配置对应不同的任务和运行结果。以下是部分配置的示例:

  • config_name: harness_arc_challenge_25

    • splits:
      • 2024_02_14T16_28_10.749584
      • 2024_02_14T16_46_48.387931
      • 2024_02_14T17_09_33.259511
      • latest
    • paths:
      • **/details_harness|arc:challenge|25_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|arc:challenge|25_2024-02-14T16-46-48.387931.parquet
      • **/details_harness|arc:challenge|25_2024-02-14T17-09-33.259511.parquet
      • **/details_harness|arc:challenge|25_2024-02-14T17-09-33.259511.parquet
  • config_name: harness_gsm8k_5

    • splits:
      • 2024_02_14T16_28_10.749584
      • 2024_02_14T16_46_48.387931
      • 2024_02_14T17_09_33.259511
      • latest
    • paths:
      • **/details_harness|gsm8k|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|gsm8k|5_2024-02-14T16-46-48.387931.parquet
      • **/details_harness|gsm8k|5_2024-02-14T17-09-33.259511.parquet
      • **/details_harness|gsm8k|5_2024-02-14T17-09-33.259511.parquet
  • config_name: harness_hellaswag_10

    • splits:
      • 2024_02_14T16_28_10.749584
      • 2024_02_14T16_46_48.387931
      • 2024_02_14T17_09_33.259511
      • latest
    • paths:
      • **/details_harness|hellaswag|10_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hellaswag|10_2024-02-14T16-46-48.387931.parquet
      • **/details_harness|hellaswag|10_2024-02-14T17-09-33.259511.parquet
      • **/details_harness|hellaswag|10_2024-02-14T17-09-33.259511.parquet
  • config_name: harness_hendrycksTest_5

    • splits:
      • 2024_02_14T16_28_10.749584
      • 2024_02_14T16_46_48.387931
      • 2024_02_14T17_09_33.259511
      • latest
    • paths:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-international_law|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-14T16-28-10.749584.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2024-02-14T16-28-10.749584.parquet
      • **/details_har
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