five

open-llm-leaderboard-old/details_jondurbin__airoboros-33b-gpt4-1.4

收藏
Hugging Face2023-10-22 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_jondurbin__airoboros-33b-gpt4-1.4
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型jondurbin/airoboros-33b-gpt4-1.4时自动生成的,评估过程在Open LLM Leaderboard上进行。数据集由64个配置组成,每个配置对应一个评估任务。数据集由3次运行生成,每次运行的结果作为特定配置中的一个分割,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,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。

该数据集是在评估模型jondurbin/airoboros-33b-gpt4-1.4时自动生成的,评估过程在Open LLM Leaderboard上进行。数据集由64个配置组成,每个配置对应一个评估任务。数据集由3次运行生成,每次运行的结果作为特定配置中的一个分割,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,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

数据集来源

该数据集是在对模型 jondurbin/airoboros-33b-gpt4-1.4 进行评估运行期间自动创建的,评估运行在 Open LLM Leaderboard 上进行。

数据集组成

数据集由 64 个配置组成,每个配置对应一个评估任务。数据集从 3 次运行中创建,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。

额外配置

一个额外的配置 "results" 存储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

要加载特定运行的详细信息,可以使用以下代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jondurbin__airoboros-33b-gpt4-1.4", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-22T23:35:00.134396 运行的最新结果: python { "all": { "em": 0.008074664429530202, "em_stderr": 0.0009165188135511226, "f1": 0.07536493288590619, "f1_stderr": 0.0016308549138484363, "acc": 0.4482593962444343, "acc_stderr": 0.010265777447066696 }, "harness|drop|3": { "em": 0.008074664429530202, "em_stderr": 0.0009165188135511226, "f1": 0.07536493288590619, "f1_stderr": 0.0016308549138484363 }, "harness|gsm8k|5": { "acc": 0.11751326762699014, "acc_stderr": 0.008870331256489982 }, "harness|winogrande|5": { "acc": 0.7790055248618785, "acc_stderr": 0.011661223637643412 } }

配置详情

以下是数据集的配置详情:

配置列表

  • harness_arc_challenge_25

    • 分割: 2023_07_31T12_50_28.372166
      • 路径: **/details_harness|arc:challenge|25_2023-07-31T12:50:28.372166.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-07-31T12:50:28.372166.parquet
  • harness_drop_3

    • 分割: 2023_10_22T20_41_55.992984
      • 路径: **/details_harness|drop|3_2023-10-22T20-41-55.992984.parquet
    • 分割: 2023_10_22T23_35_00.134396
      • 路径: **/details_harness|drop|3_2023-10-22T23-35-00.134396.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-10-22T23-35-00.134396.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_22T20_41_55.992984
      • 路径: **/details_harness|gsm8k|5_2023-10-22T20-41-55.992984.parquet
    • 分割: 2023_10_22T23_35_00.134396
      • 路径: **/details_harness|gsm8k|5_2023-10-22T23-35-00.134396.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-10-22T23-35-00.134396.parquet
  • harness_hellaswag_10

    • 分割: 2023_07_31T12_50_28.372166
      • 路径: **/details_harness|hellaswag|10_2023-07-31T12:50:28.372166.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-07-31T12:50:28.372166.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_07_31T12_50_28.372166
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-management|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-31T12:50:28.372166.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-31T12:50:28.372166.parquet
        • `**/details_harness|hendrycksTest-nutrition|5_2023-07-31T12:50:28.372
二维码
社区交流群
二维码
科研交流群
商业服务