five

open-llm-leaderboard/details_WizardLM__WizardLM-13B-V1.1

收藏
Hugging Face2023-10-28 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_WizardLM__WizardLM-13B-V1.1
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WizardLM/WizardLM-13B-V1.1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,每个配置对应一个评估任务。它由3次运行生成,每次运行在每个配置中表示为特定的分割,分割名称使用运行的时间戳。train分割始终指向最新的结果。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。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集名称

Evaluation run of WizardLM/WizardLM-13B-V1.1

数据集摘要

该数据集是在对模型WizardLM/WizardLM-13B-V1.1Open LLM Leaderboard上的评估运行期间自动创建的。

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。
  • 数据集由3次运行创建,每次运行可以在每个配置中找到一个特定的分割,分割名称使用运行的时间戳。
  • "train"分割始终指向最新的结果。
  • 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_WizardLM__WizardLM-13B-V1.1", "harness_winogrande_5", split="train")

最新结果

这些是最新结果(来自2023-10-28T23:24:10.120000运行): python { "all": { "em": 0.24213506711409397, "em_stderr": 0.004386967355552305, "f1": 0.3075335570469809, "f1_stderr": 0.0043568221171957165, "acc": 0.41585700582764323, "acc_stderr": 0.00984029249742667 }, "harness|drop|3": { "em": 0.24213506711409397, "em_stderr": 0.004386967355552305, "f1": 0.3075335570469809, "f1_stderr": 0.0043568221171957165 }, "harness|gsm8k|5": { "acc": 0.08112206216830932, "acc_stderr": 0.007520395797922653 }, "harness|winogrande|5": { "acc": 0.7505919494869772, "acc_stderr": 0.012160189196930687 } }

配置详情

  • config_name: harness_arc_challenge_25

    • split: 2023_07_26T14_16_17.821348
      • path: **/details_harness|arc:challenge|25_2023-07-26T14:16:17.821348.parquet
    • split: latest
      • path: **/details_harness|arc:challenge|25_2023-07-26T14:16:17.821348.parquet
  • config_name: harness_drop_3

    • split: 2023_10_18T15_36_34.719946
      • path: **/details_harness|drop|3_2023-10-18T15-36-34.719946.parquet
    • split: 2023_10_28T23_24_10.120000
      • path: **/details_harness|drop|3_2023-10-28T23-24-10.120000.parquet
    • split: latest
      • path: **/details_harness|drop|3_2023-10-28T23-24-10.120000.parquet
  • config_name: harness_gsm8k_5

    • split: 2023_10_18T15_36_34.719946
      • path: **/details_harness|gsm8k|5_2023-10-18T15-36-34.719946.parquet
    • split: 2023_10_28T23_24_10.120000
      • path: **/details_harness|gsm8k|5_2023-10-28T23-24-10.120000.parquet
    • split: latest
      • path: **/details_harness|gsm8k|5_2023-10-28T23-24-10.120000.parquet
  • config_name: harness_hellaswag_10

    • split: 2023_07_26T14_16_17.821348
      • path: **/details_harness|hellaswag|10_2023-07-26T14:16:17.821348.parquet
    • split: latest
      • path: **/details_harness|hellaswag|10_2023-07-26T14:16:17.821348.parquet
  • config_name: harness_hendrycksTest_5

    • split: 2023_07_26T14_16_17.821348
      • path:
        • **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-anatomy|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-astronomy|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-business_ethics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_biology|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_chemistry|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_computer_science|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_mathematics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_medicine|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-college_physics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-computer_security|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-econometrics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-formal_logic|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-global_facts|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_biology|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_european_history|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_geography|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_physics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_psychology|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_statistics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_us_history|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-high_school_world_history|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-human_aging|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-human_sexuality|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-international_law|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-jurisprudence|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-logical_fallacies|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-machine_learning|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-management|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-marketing|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-medical_genetics|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-miscellaneous|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-moral_disputes|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-moral_scenarios|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-nutrition|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-philosophy|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness|hendrycksTest-prehistory|5_2023-07-26T14:16:17.821348.parquet
        • **/details_harness
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