five

open-llm-leaderboard/details_Weyaxi__Samantha-Nebula-7B

收藏
Hugging Face2023-10-24 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_Weyaxi__Samantha-Nebula-7B
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Weyaxi/Samantha-Nebula-7B进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个评估任务。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,并用于在Open LLM Leaderboard上计算和显示聚合指标。

This dataset was automatically created during the evaluation of the model Weyaxi/Samantha-Nebula-7B on the Open LLM Leaderboard. It comprises 64 configurations, each corresponding to a single evaluation task. The dataset is generated from two runs, where the results of each run are stored as a split within its respective configuration, with the split name being the timestamp of the run. The 'train' split always references the most recent results. Additionally, there exists a configuration named 'results' that stores the aggregated results across all runs and is utilized to compute 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

该数据集是在评估模型 Weyaxi/Samantha-Nebula-7BOpen LLM Leaderboard 上的运行过程中自动创建的。

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 2 次运行创建,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 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_Weyaxi__Samantha-Nebula-7B", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-24T22:52:33.668661 运行的最新结果

python { "all": { "em": 0.3792994966442953, "em_stderr": 0.004969032454438954, "f1": 0.4256501677852355, "f1_stderr": 0.0048455756354128885, "acc": 0.42229140848972546, "acc_stderr": 0.010604861041151385 }, "harness|drop|3": { "em": 0.3792994966442953, "em_stderr": 0.004969032454438954, "f1": 0.4256501677852355, "f1_stderr": 0.0048455756354128885 }, "harness|gsm8k|5": { "acc": 0.11372251705837756, "acc_stderr": 0.008744810131034036 }, "harness|winogrande|5": { "acc": 0.7308602999210734, "acc_stderr": 0.012464911951268734 } }

配置详情

  • harness_arc_challenge_25

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|arc:challenge|25_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-10-09T12-36-46.129297.parquet
  • harness_drop_3

    • 分割:2023_10_24T22_52_33.668661
    • 路径:**/details_harness|drop|3_2023-10-24T22-52-33.668661.parquet
    • 分割:latest
    • 路径:**/details_harness|drop|3_2023-10-24T22-52-33.668661.parquet
  • harness_gsm8k_5

    • 分割:2023_10_24T22_52_33.668661
    • 路径:**/details_harness|gsm8k|5_2023-10-24T22-52-33.668661.parquet
    • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-10-24T22-52-33.668661.parquet
  • harness_hellaswag_10

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hellaswag|10_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T12-36-46.129297.parquet 等 40 个文件
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T12-36-46.129297.parquet 等 40 个文件
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_anatomy_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_astronomy_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_business_ethics_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_clinical_knowledge_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_biology_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_chemistry_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_computer_science_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_mathematics_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_medicine_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_college_physics_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_computer_security_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_conceptual_physics_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_econometrics_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-10-09T12-36-46.129297.parquet
  • harness_hendrycksTest_electrical_engineering_5

    • 分割:2023_10_09T12_36_46.129297
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-10-09T12-36-46.129297.parquet
    • 分割:latest
    • 路径:`**/details_harness|hendrycksTest-electrical
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