five

open-llm-leaderboard/details_YeungNLP__firefly-llama-13b-v1.2

收藏
Hugging Face2023-09-23 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_YeungNLP__firefly-llama-13b-v1.2
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YeungNLP/firefly-llama-13b-v1.2时自动创建的,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,每次运行的结果作为一个特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。此外,还有一个results配置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。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集简介

该数据集是在评估模型 YeungNLP/firefly-llama-13b-v1.2Open LLM Leaderboard 上的运行过程中自动创建的。

数据集结构

  • 配置数量:64个配置,每个配置对应一个评估任务。
  • 运行次数:数据集由2次运行创建。每个运行在每个配置中作为一个特定的分割存在,分割名称使用运行的时间戳。
  • 训练分割:"train" 分割始终指向最新的结果。
  • 结果配置:一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_YeungNLP__firefly-llama-13b-v1.2", "harness_winogrande_5", split="train")

最新结果

以下是 2023-09-23T00:40:07.010521 运行的最新结果: python { "all": { "em": 0.15614513422818793, "em_stderr": 0.0037173868511430597, "f1": 0.2505851510067118, "f1_stderr": 0.0038733830582179693, "acc": 0.4198188936752808, "acc_stderr": 0.009751908892731628 }, "harness|drop|3": { "em": 0.15614513422818793, "em_stderr": 0.0037173868511430597, "f1": 0.2505851510067118, "f1_stderr": 0.0038733830582179693 }, "harness|gsm8k|5": { "acc": 0.0803639120545868, "acc_stderr": 0.007488258573239077 }, "harness|winogrande|5": { "acc": 0.7592738752959748, "acc_stderr": 0.01201555921222418 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|arc:challenge|25_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-24T14:08:16.111651.parquet
  • harness_drop_3

    • 分割:2023_09_23T00_40_07.010521
    • 路径:**/details_harness|drop|3_2023-09-23T00-40-07.010521.parquet
    • 分割:latest
    • 路径:**/details_harness|drop|3_2023-09-23T00-40-07.010521.parquet
  • harness_gsm8k_5

    • 分割:2023_09_23T00_40_07.010521
    • 路径:**/details_harness|gsm8k|5_2023-09-23T00-40-07.010521.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-09-23T00-40-07.010521.parquet
  • harness_hellaswag_10

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hellaswag|10_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-24T14:08:16.111651.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-24T14:08:16.111651.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_07_24T14_08_16.111651
    • 路径:`**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-24T14:08:16.111651
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