five

open-llm-leaderboard-old/details_Charlie911__vicuna-7b-v1.5-lora-mixed-datasets-time-unit

收藏
Hugging Face2023-10-28 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Charlie911__vicuna-7b-v1.5-lora-mixed-datasets-time-unit
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Charlie911/vicuna-7b-v1.5-lora-mixed-datasets-time-unit时自动生成的,用于Open LLM Leaderboard的评估。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,用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在评估模型Charlie911/vicuna-7b-v1.5-lora-mixed-datasets-time-unit时自动生成的,用于Open LLM Leaderboard的评估。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,用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 Charlie911/vicuna-7b-v1.5-lora-mixed-datasets-time-unit 进行评估运行期间自动创建的,用于 Open LLM Leaderboard 上的评估。

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。
  • 数据来源:数据集由2次运行创建,每次运行对应一个特定的时间戳。
  • 数据分割:每个配置包含不同的时间戳分割,其中“train”分割指向最新的结果。
  • 结果汇总:一个额外的配置“results”存储所有运行的汇总结果,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_Charlie911__vicuna-7b-v1.5-lora-mixed-datasets-time-unit", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-28T09:09:00.701109 运行的最新结果: python { "all": { "em": 0.004928691275167785, "em_stderr": 0.0007171872517059817, "f1": 0.06610213926174507, "f1_stderr": 0.001553905671666344, "acc": 0.4026417372707673, "acc_stderr": 0.009752392640502771 }, "harness|drop|3": { "em": 0.004928691275167785, "em_stderr": 0.0007171872517059817, "f1": 0.06610213926174507, "f1_stderr": 0.001553905671666344 }, "harness|gsm8k|5": { "acc": 0.0712661106899166, "acc_stderr": 0.007086462127954495 }, "harness|winogrande|5": { "acc": 0.734017363851618, "acc_stderr": 0.012418323153051046 } }

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_10_08T16_13_20.175189
      • 路径:**/details_harness|arc:challenge|25_2023-10-08T16-13-20.175189.parquet
    • 分割:latest
      • 路径:**/details_harness|arc:challenge|25_2023-10-08T16-13-20.175189.parquet
  • harness_drop_3

    • 分割:2023_10_28T09_09_00.701109
      • 路径:**/details_harness|drop|3_2023-10-28T09-09-00.701109.parquet
    • 分割:latest
      • 路径:**/details_harness|drop|3_2023-10-28T09-09-00.701109.parquet
  • harness_gsm8k_5

    • 分割:2023_10_28T09_09_00.701109
      • 路径:**/details_harness|gsm8k|5_2023-10-28T09-09-00.701109.parquet
    • 分割:latest
      • 路径:**/details_harness|gsm8k|5_2023-10-28T09-09-00.701109.parquet
  • harness_hellaswag_10

    • 分割:2023_10_08T16_13_20.175189
      • 路径:**/details_harness|hellaswag|10_2023-10-08T16-13-20.175189.parquet
    • 分割:latest
      • 路径:**/details_harness|hellaswag|10_2023-10-08T16-13-20.175189.parquet
  • harness_hendrycksTest_5

    • 分割:2023_10_08T16_13_20.175189
      • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-formal_logic|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-global_facts|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_biology|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_chemistry|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_computer_science|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_european_history|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_geography|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_mathematics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_physics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_psychology|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_statistics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_us_history|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-high_school_world_history|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-human_aging|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-human_sexuality|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-international_law|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-jurisprudence|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-logical_fallacies|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-machine_learning|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-management|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-marketing|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-medical_genetics|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-miscellaneous|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-moral_disputes|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-moral_scenarios|5_2023-10-08T16-13-20.175189.parquet
      • 路径:**/details_harness|hendrycksTest-nutrition|5_2023-10-08T16-13-20.175189.parquet
      • 路径:`**/details_harness|hendrycksTest-philosophy|
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