five

open-llm-leaderboard/details_TheBloke__wizard-vicuna-13B-HF

收藏
Hugging Face2023-10-22 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_TheBloke__wizard-vicuna-13B-HF
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TheBloke/wizard-vicuna-13B-HF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,每次运行的结果存储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,并用于计算和显示在Open LLM Leaderboard上的聚合指标。

This dataset was automatically created during the evaluation of the model TheBloke/wizard-vicuna-13B-HF. It contains 64 configurations, each corresponding to one evaluation task. The dataset is generated from two experimental runs, where the results of each run are stored as a split under a specific configuration, with the split name being the timestamp of the run. The `train` split always points to the latest result. Additionally, there is a configuration named `results` that stores the aggregated results across all runs, and is used to calculate and display the aggregated 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

该数据集是在对模型 TheBloke/wizard-vicuna-13B-HF 进行评估运行期间自动创建的,用于 Open LLM Leaderboard

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次运行结果组成,每次运行的结果可以在每个配置中找到,以运行的时间戳命名。
  • 最新结果:"train" 分割总是指向最新的结果。
  • 汇总结果: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_TheBloke__wizard-vicuna-13B-HF", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-22T05:16:09.820423 运行 的最新结果: python { "all": { "em": 0.0350251677852349, "em_stderr": 0.0018827287598880416, "f1": 0.10088821308724859, "f1_stderr": 0.0023095858218995214, "acc": 0.4207383077634691, "acc_stderr": 0.010104088969294184 }, "harness|drop|3": { "em": 0.0350251677852349, "em_stderr": 0.0018827287598880416, "f1": 0.10088821308724859, "f1_stderr": 0.0023095858218995214 }, "harness|gsm8k|5": { "acc": 0.0932524639878696, "acc_stderr": 0.008009688838328585 }, "harness|winogrande|5": { "acc": 0.7482241515390686, "acc_stderr": 0.012198489100259785 } }

配置详情

以下是数据集的部分配置详情:

  • harness_arc_challenge_25

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|arc:challenge|25_2023-07-18T15:41:31.806863.parquet
  • harness_drop_3

    • 分割:2023_10_22T05_16_09.820423, latest
    • 路径:**/details_harness|drop|3_2023-10-22T05-16-09.820423.parquet
  • harness_gsm8k_5

    • 分割:2023_10_22T05_16_09.820423, latest
    • 路径:**/details_harness|gsm8k|5_2023-10-22T05-16-09.820423.parquet
  • harness_hellaswag_10

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hellaswag|10_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:多个路径,例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-18T15:41:31.806863.parquet
  • harness_hendrycksTest_elementary_mathematics_5

    • 分割:2023_07_18T15_41_31.806863, latest
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-18T15:41:31.806863.parquet
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