five

open-llm-leaderboard/details_FelixChao__vicuna-7B-physics

收藏
Hugging Face2023-10-16 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_FelixChao__vicuna-7B-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Open LLM Leaderboard上对模型FelixChao/vicuna-7B-physics进行评估时自动生成的。数据集由64个配置组成,每个配置对应一个评估任务。数据集由2次运行生成,每次运行的结果都存储为特定的分割,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,还有一个名为results的配置存储了所有运行的聚合结果,用于在Open LLM Leaderboard上计算和显示聚合指标。

This dataset was automatically generated during the evaluation of the model FelixChao/vicuna-7B-physics on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to a single evaluation task. The dataset is generated from two evaluation runs, with the results of each run stored as a dedicated dataset split, where the split name uses the timestamp of the corresponding run. The "train" split always points to the most recent evaluation results. Additionally, there is a configuration named "results" that stores the aggregated results across all runs, which is utilized to compute and display the aggregate metrics on the Open LLM Leaderboard.
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 FelixChao/vicuna-7B-physicsOpen LLM Leaderboard 上的运行过程中自动创建的。

数据集结构

  • 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_FelixChao__vicuna-7B-physics", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-16T22:59:16.293660 运行的最新结果: python { "all": { "em": 0.001153523489932886, "em_stderr": 0.0003476179896857083, "f1": 0.0649444211409399, "f1_stderr": 0.001377707459666866, "acc": 0.3681106025528177, "acc_stderr": 0.009254111861396252 }, "harness|drop|3": { "em": 0.001153523489932886, "em_stderr": 0.0003476179896857083, "f1": 0.0649444211409399, "f1_stderr": 0.001377707459666866 }, "harness|gsm8k|5": { "acc": 0.04245640636846096, "acc_stderr": 0.005553837749990046 }, "harness|winogrande|5": { "acc": 0.6937647987371744, "acc_stderr": 0.012954385972802457 } }

配置详情

  • harness_arc_challenge_25

    • 分割: 2023_08_18T10_17_03.743373
    • 路径: **/details_harness|arc:challenge|25_2023-08-18T10:17:03.743373.parquet
    • 分割: latest
    • 路径: **/details_harness|arc:challenge|25_2023-08-18T10:17:03.743373.parquet
  • harness_drop_3

    • 分割: 2023_10_16T22_59_16.293660
    • 路径: **/details_harness|drop|3_2023-10-16T22-59-16.293660.parquet
    • 分割: latest
    • 路径: **/details_harness|drop|3_2023-10-16T22-59-16.293660.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_16T22_59_16.293660
    • 路径: **/details_harness|gsm8k|5_2023-10-16T22-59-16.293660.parquet
    • 分割: latest
    • 路径: **/details_harness|gsm8k|5_2023-10-16T22-59-16.293660.parquet
  • harness_hellaswag_10

    • 分割: 2023_08_18T10_17_03.743373
    • 路径: **/details_harness|hellaswag|10_2023-08-18T10:17:03.743373.parquet
    • 分割: latest
    • 路径: **/details_harness|hellaswag|10_2023-08-18T10:17:03.743373.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_08_18T10_17_03.743373
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-management|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-08-18T10:17:03.743373.parquet
      • **/details_harness|hendrycksTest-professional_medicine
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