five

open-llm-leaderboard/details_tiiuae__falcon-rw-1b

收藏
Hugging Face2023-10-25 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_tiiuae__falcon-rw-1b
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tiiuae/falcon-rw-1b进行评估时自动生成的。数据集由64个配置组成,每个配置对应一个被评估的任务。它包含2次运行的数据,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。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。README还提供了一个Python代码片段来加载数据集详细信息,并列出了特定运行的最新结果。

This dataset was automatically generated during the evaluation of the model tiiuae/falcon-rw-1b on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluated task. It contains data from 2 runs, with each run represented as a specific split within each configuration, where the split name is named after the timestamp of the run. The train split always points to the most recent results. An additional configuration named 'results' stores the aggregated results across all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard. The README also provides a Python code snippet for loading dataset details, and lists the most recent results for specific runs.
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 tiiuae/falcon-rw-1bOpen LLM Leaderboard 上的自动创建的。数据集包含64个配置,每个配置对应一个评估任务。

数据集结构

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。

数据集加载示例

以下是加载数据集的示例代码: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_tiiuae__falcon-rw-1b", "harness_winogrande_5", split="train")

最新结果

以下是2023年10月25日18:16:05.784566运行的最新结果: python { "all": { "em": 0.0010486577181208054, "em_stderr": 0.00033145814652193675, "f1": 0.0464429530201344, "f1_stderr": 0.001186214815178995, "acc": 0.31283505657403515, "acc_stderr": 0.007820275562329611 }, "harness|drop|3": { "em": 0.0010486577181208054, "em_stderr": 0.00033145814652193675, "f1": 0.0464429530201344, "f1_stderr": 0.001186214815178995 }, "harness|gsm8k|5": { "acc": 0.00530705079605762, "acc_stderr": 0.0020013057209480574 }, "harness|winogrande|5": { "acc": 0.6203630623520127, "acc_stderr": 0.013639245403711165 } }

配置详情

数据集包含多个配置,每个配置对应不同的任务和运行结果。以下是部分配置的详细信息:

配置 harness_arc_challenge_25

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|arc:challenge|25_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|arc:challenge|25_2023-09-13T16-16-44.792936.parquet

配置 harness_drop_3

  • 分割 2023_10_25T18_16_05.784566
    • 路径: **/details_harness|drop|3_2023-10-25T18-16-05.784566.parquet
  • 分割 latest
    • 路径: **/details_harness|drop|3_2023-10-25T18-16-05.784566.parquet

配置 harness_gsm8k_5

  • 分割 2023_10_25T18_16_05.784566
    • 路径: **/details_harness|gsm8k|5_2023-10-25T18-16-05.784566.parquet
  • 分割 latest
    • 路径: **/details_harness|gsm8k|5_2023-10-25T18-16-05.784566.parquet

配置 harness_hellaswag_10

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hellaswag|10_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hellaswag|10_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T16-16-44.792936.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-13T16-16-44.792936.parquet
      • ...
  • 分割 latest
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T16-16-44.792936.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-13T16-16-44.792936.parquet
      • ...

配置 harness_hendrycksTest_abstract_algebra_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_anatomy_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_astronomy_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_business_ethics_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_clinical_knowledge_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_biology_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_chemistry_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_computer_science_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_mathematics_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_medicine_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_college_physics_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_computer_security_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_conceptual_physics_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_econometrics_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-09-13T16-16-44.792936.parquet
  • 分割 latest
    • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-09-13T16-16-44.792936.parquet

配置 harness_hendrycksTest_electrical_engineering_5

  • 分割 2023_09_13T16_16_44.792936
    • 路径: `**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-13T16-16-44
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