five

open-llm-leaderboard/details_lgaalves__gpt2_platypus-camel_physics

收藏
Hugging Face2023-10-25 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_lgaalves__gpt2_platypus-camel_physics
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 lgaalves/gpt2_platypus-camel_physics 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。它由 2 次运行生成,每次运行在每个配置中表示为特定的分割,使用运行的时间戳命名。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。README 还提供了如何使用 `datasets` 库中的 `load_dataset` 函数加载数据集的示例。
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 lgaalves/gpt2_platypus-camel_physicsOpen LLM Leaderboard 上的自动创建的。

数据集组成

  • 数据集包含 64 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。
  • 一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_lgaalves__gpt2_platypus-camel_physics", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-25T13:50:32.288438 运行的最新结果: python { "all": { "em": 0.002307046979865772, "em_stderr": 0.0004913221265094493, "f1": 0.04785339765100675, "f1_stderr": 0.001366270058429369, "acc": 0.24822415153906865, "acc_stderr": 0.007026065573457936 }, "harness|drop|3": { "em": 0.002307046979865772, "em_stderr": 0.0004913221265094493, "f1": 0.04785339765100675, "f1_stderr": 0.001366270058429369 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|winogrande|5": { "acc": 0.4964483030781373, "acc_stderr": 0.014052131146915873 } }

配置详情

  • harness_arc_challenge_25

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|arc:challenge|25_2023-09-11T15-51-24.784876.parquet
  • harness_drop_3

    • 分片: 2023_10_25T13_50_32.288438, latest
    • 路径: **/details_harness|drop|3_2023-10-25T13-50-32.288438.parquet
  • harness_gsm8k_5

    • 分片: 2023_10_25T13_50_32.288438, latest
    • 路径: **/details_harness|gsm8k|5_2023-10-25T13-50-32.288438.parquet
  • harness_hellaswag_10

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hellaswag|10_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: 多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_anatomy_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_astronomy_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_biology_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_college_physics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_computer_security_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_econometrics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-11T15-51-24.784876.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分片: 2023_09_11T15_51_24.784876, latest
    • 路径: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-11T15-51-24.784876.parquet
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