five

open-llm-leaderboard/details_TRI-ML__mamba-7b-rw

收藏
Hugging Face2024-05-09 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TRI-ML__mamba-7b-rw
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型TRI-ML/mamba-7b-rw进行评估时自动创建的。它由62个配置组成,每个配置对应一个被评估的任务。数据集由2次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。

该数据集是在Open LLM Leaderboard上对模型TRI-ML/mamba-7b-rw进行评估时自动创建的。它由62个配置组成,每个配置对应一个被评估的任务。数据集由2次运行生成,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果,这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。可以使用`datasets`库中的`load_dataset`函数加载该数据集。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在评估模型 TRI-ML/mamba-7b-rwOpen LLM Leaderboard 上的自动创建的。数据集包含 62 个配置,每个配置对应一个评估任务。数据集从 2 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。

数据集结构

配置

  • harness_arc_challenge_25

    • 分割: 2024_05_09T19_27_38.920738, latest
    • 路径: **/details_harness|arc:challenge|25_2024-05-09T19-27-38.920738.parquet
  • harness_gsm8k_5

    • 分割: 2024_05_06T16_37_03.145530, latest
    • 路径: **/details_harness|gsm8k|5_2024-05-06T16-37-03.145530.parquet
  • harness_hellaswag_10

    • 分割: 2024_05_09T19_27_38.920738, latest
    • 路径: **/details_harness|hellaswag|10_2024-05-09T19-27-38.920738.parquet
  • harness_hendrycksTest_5

    • 分割: 2024_05_09T19_27_38.920738, latest
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-05-09T19-27-38.920738.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-05-09T19-27-38.920738.parquet

最新结果

以下是 2024-05-09T19:27:38.920738 运行 的最新结果:

python { "all": { "acc": 0.3370893001475179, "acc_stderr": 0.0337911620364635, "acc_norm": 0.3411283118868055, "acc_norm_stderr": 0.03377519866428805, "mc1": 0.23133414932680538, "mc1_stderr": 0.014761945174862677, "mc2": 0.32152254703544064, "mc2_stderr": 0.013194827085964842 }, "harness|arc:challenge|25": { "acc": 0.48378839590443684, "acc_stderr": 0.01460370856741494, "acc_norm": 0.515358361774744, "acc_norm_stderr": 0.014604496129394906 }, "harness|hellaswag|10": { "acc": 0.5989842660824537, "acc_stderr": 0.004891025533633034, "acc_norm": 0.8057159928301135, "acc_norm_stderr": 0.003948399013301679 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3851851851851852, "acc_stderr": 0.042039210401562783, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.042039210401562783 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.32894736842105265, "acc_stderr": 0.03823428969926605, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.03823428969926605 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.39245283018867927, "acc_stderr": 0.03005258057955784, "acc_norm": 0.39245283018867927, "acc_norm_stderr": 0.03005258057955784 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3680555555555556, "acc_stderr": 0.040329990539607195, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.040329990539607195 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.16, "acc_stderr": 0.03684529491774709, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165044, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165044 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3063583815028902, "acc_stderr": 0.03514942551267438, "acc_norm": 0.3063583815028902, "acc_norm_stderr": 0.03514942551267438 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.19607843137254902, "acc_stderr": 0.03950581861179963, "acc_norm": 0.19607843137254902, "acc_norm_stderr": 0.03950581861179963 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3446808510638298, "acc_stderr": 0.03106898596312215, "acc_norm": 0.3446808510638298, "acc_norm_stderr": 0.03106898596312215 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.3724137931034483, "acc_stderr": 0.04028731532947559, "acc_norm": 0.3724137931034483, "acc_norm_stderr": 0.04028731532947559 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2328042328042328, "acc_stderr": 0.02176596167215453, "acc_norm": 0.

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