five

open-llm-leaderboard/details_chargoddard__llama-2-34b-uncode

收藏
Hugging Face2023-10-17 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_chargoddard__llama-2-34b-uncode
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chargoddard/llama-2-34b-uncode进行评估时自动生成的。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,每次运行的结果作为特定配置中的一个分割,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 chargoddard/llama-2-34b-uncode on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluation task. The dataset is generated from two runs, where the results of each run serve as a split under a specific configuration, with the split name being the timestamp of the run. The `train` split always points to the most recent results. In addition, there is a configuration named `results` that stores the aggregated results across all runs, which is used to calculate and display 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 chargoddard/llama-2-34b-uncodeOpen 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。
  • 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_chargoddard__llama-2-34b-uncode", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 来自 2023-10-17T09:49:44.237911 运行: python { "all": { "em": 0.0014681208053691276, "em_stderr": 0.000392104219029832, "f1": 0.054323615771812044, "f1_stderr": 0.001268355641976372, "acc": 0.47561084340161075, "acc_stderr": 0.01172411036273294 }, "harness|drop|3": { "em": 0.0014681208053691276, "em_stderr": 0.000392104219029832, "f1": 0.054323615771812044, "f1_stderr": 0.001268355641976372 }, "harness|gsm8k|5": { "acc": 0.20773313115996966, "acc_stderr": 0.011174572716705883 }, "harness|winogrande|5": { "acc": 0.7434885556432518, "acc_stderr": 0.012273648008759998 } }

配置详情

以下是部分配置及其数据文件路径:

  • harness_arc_challenge_25

    • 分割: 2023_08_29T02_22_47.016201
      • 路径: **/details_harness|arc:challenge|25_2023-08-29T02:22:47.016201.parquet
    • 分割: latest
      • 路径: **/details_harness|arc:challenge|25_2023-08-29T02:22:47.016201.parquet
  • harness_drop_3

    • 分割: 2023_10_17T09_49_44.237911
      • 路径: **/details_harness|drop|3_2023-10-17T09-49-44.237911.parquet
    • 分割: latest
      • 路径: **/details_harness|drop|3_2023-10-17T09-49-44.237911.parquet
  • harness_gsm8k_5

    • 分割: 2023_10_17T09_49_44.237911
      • 路径: **/details_harness|gsm8k|5_2023-10-17T09-49-44.237911.parquet
    • 分割: latest
      • 路径: **/details_harness|gsm8k|5_2023-10-17T09-49-44.237911.parquet
  • harness_hellaswag_10

    • 分割: 2023_08_29T02_22_47.016201
      • 路径: **/details_harness|hellaswag|10_2023-08-29T02:22:47.016201.parquet
    • 分割: latest
      • 路径: **/details_harness|hellaswag|10_2023-08-29T02:22:47.016201.parquet
  • harness_hendrycksTest_5

    • 分割: 2023_08_29T02_22_47.016201
      • 路径:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-management|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-08-29T02:22:47.016201.parquet
        • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T02:22:47.016201.parquet
        • `**/details_harness|hendrycksTest-professional_law|5_2023-08-29T02:22:4
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