dongyoung4091/shp-generated_flan_t5_large_flan_t5_zeroshot_sileod

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: prompt
dtype: string
- name: response
dtype: string
- name: zeroshot_helpfulness
dtype: float64
- name: zeroshot_specificity
dtype: float64
- name: zeroshot_intent
dtype: float64
- name: zeroshot_factuality
dtype: float64
- name: zeroshot_easy-to-understand
dtype: int64
- name: zeroshot_relevance
dtype: int64
- name: zeroshot_readability
dtype: int64
- name: zeroshot_enough-detail
dtype: int64
- name: 'zeroshot_biased:'
dtype: float64
- name: zeroshot_fail-to-consider-individual-preferences
dtype: float64
- name: zeroshot_repetetive
dtype: float64
- name: zeroshot_fail-to-consider-context
dtype: float64
- name: zeroshot_too-long
dtype: int64
- name: external_rm1
dtype: float64
splits:
- name: train
num_bytes: 29701040
num_examples: 25600
download_size: 2057759
dataset_size: 29701040
---
# Dataset Card for "shp-generated_flan_t5_large_flan_t5_zeroshot_sileod"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

配置

• 配置名称: default
• 数据文件:
  • 分割: train
  • 路径: data/train-*

数据集信息

• 特征:
  • 名称: prompt
    • 数据类型: string
  • 名称: response
    • 数据类型: string
  • 名称: zeroshot_helpfulness
    • 数据类型: float64
  • 名称: zeroshot_specificity
    • 数据类型: float64
  • 名称: zeroshot_intent
    • 数据类型: float64
  • 名称: zeroshot_factuality
    • 数据类型: float64
  • 名称: zeroshot_easy-to-understand
    • 数据类型: int64
  • 名称: zeroshot_relevance
    • 数据类型: int64
  • 名称: zeroshot_readability
    • 数据类型: int64
  • 名称: zeroshot_enough-detail
    • 数据类型: int64
  • 名称: zeroshot_biased:
    • 数据类型: float64
  • 名称: zeroshot_fail-to-consider-individual-preferences
    • 数据类型: float64
  • 名称: zeroshot_repetetive
    • 数据类型: float64
  • 名称: zeroshot_fail-to-consider-context
    • 数据类型: float64
  • 名称: zeroshot_too-long
    • 数据类型: int64
  • 名称: external_rm1
    • 数据类型: float64

分割

• 名称: train
  • 字节数: 29701040
  • 样本数: 25600

数据集大小

• 下载大小: 2057759
• 数据集大小: 29701040