five

open-llm-leaderboard-old/details_AA051610__AZG

收藏
Hugging Face2023-12-09 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_AA051610__AZG
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AA051610/AZG的评估运行期间自动创建的,用于Open LLM Leaderboard。数据集由63个配置组成,每个配置对应一个评估任务。数据集由1次运行创建,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。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。

该数据集是在模型AA051610/AZG的评估运行期间自动创建的,用于Open LLM Leaderboard。数据集由63个配置组成,每个配置对应一个评估任务。数据集由1次运行创建,每次运行可以在每个配置中找到,运行的时间戳作为分割名称。train分割始终指向最新结果。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。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

该数据集是在模型 AA051610/AZGOpen LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置,每个配置对应一个评估任务。数据集从 1 次运行中创建,每个运行可以在每个配置中作为一个特定的分片找到,分片名称使用运行的时间戳。"train" 分片始终指向最新的结果。

数据集结构

数据集包含以下配置:

  • harness_arc_challenge_25

    • 分片:2023_12_09T22_11_18.691101
    • 路径:**/details_harness|arc:challenge|25_2023-12-09T22-11-18.691101.parquet
    • 分片:latest
    • 路径:**/details_harness|arc:challenge|25_2023-12-09T22-11-18.691101.parquet
  • harness_gsm8k_5

    • 分片:2023_12_09T22_11_18.691101
    • 路径:**/details_harness|gsm8k|5_2023-12-09T22-11-18.691101.parquet
    • 分片:latest
    • 路径:**/details_harness|gsm8k|5_2023-12-09T22-11-18.691101.parquet
  • harness_hellaswag_10

    • 分片:2023_12_09T22_11_18.691101
    • 路径:**/details_harness|hellaswag|10_2023-12-09T22-11-18.691101.parquet
    • 分片:latest
    • 路径:**/details_harness|hellaswag|10_2023-12-09T22-11-18.691101.parquet
  • harness_hendrycksTest_5

    • 分片:2023_12_09T22_11_18.691101
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-12-09T22-11-18.691101.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-09T22-11-18.691101.parquet

最新结果

以下是 2023-12-09T22:11:18.691101 运行的最新结果:

python { "all": { "acc": 0.6997224830510826, "acc_stderr": 0.03037702672483155, "acc_norm": 0.7036495225534056, "acc_norm_stderr": 0.030966589072480434, "mc1": 0.38310893512851896, "mc1_stderr": 0.017018461679389855, "mc2": 0.538427969031974, "mc2_stderr": 0.015499026242399048 }, "harness|arc:challenge|25": { "acc": 0.5981228668941979, "acc_stderr": 0.014327268614578274, "acc_norm": 0.628839590443686, "acc_norm_stderr": 0.014117971901142822 }, "harness|hellaswag|10": { "acc": 0.619398526190002, "acc_stderr": 0.0048454245247640405, "acc_norm": 0.8201553475403306, "acc_norm_stderr": 0.003832731017592104 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6222222222222222, "acc_stderr": 0.04188307537595853, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595853 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8289473684210527, "acc_stderr": 0.030643607071677088, "acc_norm": 0.8289473684210527, "acc_norm_stderr": 0.030643607071677088 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7358490566037735, "acc_stderr": 0.027134291628741706, "acc_norm": 0.7358490566037735, "acc_norm_stderr": 0.027134291628741706 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7986111111111112, "acc_stderr": 0.033536474697138406, "acc_norm": 0.7986111111111112, "acc_norm_stderr": 0.033536474697138406 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932261, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932261 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7063829787234043, "acc_stderr": 0.029771642712491227, "acc_norm": 0.7063829787234043, "acc_norm_stderr": 0.029771642712491227 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.543859649122807, "acc_stderr": 0.046854730419077895, "acc_norm": 0.543859649122807, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7103448275862069, "acc_stderr": 0.03780019230438015, "acc_norm": 0.7103448275862069, "acc_norm_stderr": 0.0378

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