five

open-llm-leaderboard/details_abhishek__llama2guanacotest

收藏
Hugging Face2023-09-22 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_abhishek__llama2guanacotest
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abhishek/llama2guanacotest进行评估时自动创建的。数据集由64个配置组成,每个配置对应一个特定的评估任务。数据集是从2次运行中生成的,每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。此外,名为results的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还提供了如何使用`datasets`库中的`load_dataset`函数加载运行细节的示例。

This dataset was automatically created during the evaluation of the model abhishek/llama2guanacotest on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to a specific evaluation task. The dataset is generated from 2 runs, where each run is represented as a specific split under each configuration. The 'train' split always points to the most recent results. Additionally, the configuration named 'results' stores the aggregated results across all runs, which are used to calculate and display the aggregate metrics on the Open LLM Leaderboard. The README also provides examples of how to use the `load_dataset` function from the `datasets` library to load the run details.
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 abhishek/llama2guanacotestOpen 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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_abhishek__llama2guanacotest", "harness_winogrande_5", split="train")

最新结果

以下是 最新结果 的示例: python { "all": { "em": 0.1018246644295302, "em_stderr": 0.0030970392367407284, "f1": 0.15182571308724796, "f1_stderr": 0.0032356577343186617, "acc": 0.42458141676534983, "acc_stderr": 0.010661835808025592 }, "harness|drop|3": { "em": 0.1018246644295302, "em_stderr": 0.0030970392367407284, "f1": 0.15182571308724796, "f1_stderr": 0.0032356577343186617 }, "harness|gsm8k|5": { "acc": 0.11751326762699014, "acc_stderr": 0.008870331256489988 }, "harness|winogrande|5": { "acc": 0.7316495659037096, "acc_stderr": 0.012453340359561195 } }

配置详情

以下是数据集的部分配置详情:

配置名称:harness_arc_challenge_25

  • 分割:2023_08_17T13_26_15.590917
    • 路径:**/details_harness|arc:challenge|25_2023-08-17T13:26:15.590917.parquet
  • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-08-17T13:26:15.590917.parquet

配置名称:harness_drop_3

  • 分割:2023_09_22T17_34_42.809014
    • 路径:**/details_harness|drop|3_2023-09-22T17-34-42.809014.parquet
  • 分割:latest
    • 路径:**/details_harness|drop|3_2023-09-22T17-34-42.809014.parquet

配置名称:harness_gsm8k_5

  • 分割:2023_09_22T17_34_42.809014
    • 路径:**/details_harness|gsm8k|5_2023-09-22T17-34-42.809014.parquet
  • 分割:latest
    • 路径:**/details_harness|gsm8k|5_2023-09-22T17-34-42.809014.parquet

配置名称:harness_hellaswag_10

  • 分割:2023_08_17T13_26_15.590917
    • 路径:**/details_harness|hellaswag|10_2023-08-17T13:26:15.590917.parquet
  • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-08-17T13:26:15.590917.parquet

配置名称:harness_hendrycksTest_5

  • 分割:2023_08_17T13_26_15.590917
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_physics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_psychology|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_statistics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_us_history|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-high_school_world_history|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-human_aging|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-human_sexuality|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-international_law|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-jurisprudence|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-logical_fallacies|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-machine_learning|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-management|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-marketing|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-medical_genetics|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-miscellaneous|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-moral_disputes|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-moral_scenarios|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-nutrition|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-philosophy|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-prehistory|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-professional_accounting|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-professional_law|5_2023-08-17T13:26:15.590917.parquet
      • **/details_harness|hendrycksTest-professional_medicine|5_2023-08-17T13:26:15.590917.parquet
      • `**/details_harness|hendrycksTest-professional_psychology|5_2023-08-17T13:26:15.590917.par
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