five

open-llm-leaderboard-old/details_yeontaek__Platypus2xOpenOrca-13B-IA3

收藏
Hugging Face2023-10-16 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_yeontaek__Platypus2xOpenOrca-13B-IA3
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yeontaek/Platypus2xOpenOrca-13B-IA3时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果存储在不同的分割中,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,用于存储所有运行的聚合结果,并在Open LLM Leaderboard上显示聚合指标。

该数据集是在评估模型yeontaek/Platypus2xOpenOrca-13B-IA3时自动创建的,主要用于在Open LLM Leaderboard上展示评估结果。数据集包含64个配置,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果存储在不同的分割中,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,用于存储所有运行的聚合结果,并在Open LLM Leaderboard上显示聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 yeontaek/Platypus2xOpenOrca-13B-IA3 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

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

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_yeontaek__Platypus2xOpenOrca-13B-IA3", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-16T07:16:50.024498 运行的最新结果: python { "all": { "em": 0.004299496644295302, "em_stderr": 0.0006700586558629855, "f1": 0.07570155201342293, "f1_stderr": 0.0016454710303896235, "acc": 0.44469214138811486, "acc_stderr": 0.010351218038230171 }, "harness|drop|3": { "em": 0.004299496644295302, "em_stderr": 0.0006700586558629855, "f1": 0.07570155201342293, "f1_stderr": 0.0016454710303896235 }, "harness|gsm8k|5": { "acc": 0.11827141774071266, "acc_stderr": 0.008895075852434951 }, "harness|winogrande|5": { "acc": 0.771112865035517, "acc_stderr": 0.01180736022402539 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|arc:challenge|25_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-08-18T07:56:15.654577.parquet
  • harness_drop_3

    • 分割:2023_10_16T07_16_50.024498
    • 路径:**/details_harness|drop|3_2023-10-16T07-16-50.024498.parquet
    • 分割:latest
    • 路径:**/details_harness|drop|3_2023-10-16T07-16-50.024498.parquet
  • harness_gsm8k_5

    • 分割:2023_10_16T07_16_50.024498
    • 路径:**/details_harness|gsm8k|5_2023-10-16T07-16-50.024498.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-10-16T07-16-50.024498.parquet
  • harness_hellaswag_10

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hellaswag|10_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-18T07:56:15.654577.parquet 等 40 个文件
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-18T07:56:15.654577.parquet 等 40 个文件
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-08-18T07:56:15.654577.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-08-18T07:56:15.654577.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_08_18T07_56_15.654577
    • 路径:`**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-18T0
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