haoranli-ml/sanity_check_subset_single_policy_run
收藏Hugging Face2026-03-21 更新2026-03-29 收录
下载链接：
https://hf-mirror.com/datasets/haoranli-ml/sanity_check_subset_single_policy_run
下载链接
链接失效反馈官方服务：
资源简介：
---
dataset_info:
features:
- name: problem
dtype: string
- name: answer
dtype: string
- name: prefix
dtype: string
- name: prefix_end_index
dtype: int64
- name: response
dtype: string
- name: original_mean_reward_of_question
dtype: float64
- name: original_mean_reward_source
dtype: string
- name: sources
list: string
- name: correct
dtype: bool
- name: difficulty
dtype: string
- name: prefix_tokens
dtype: int64
- name: branch_rollouts
list: string
- name: branch_rewards
list: int64
- name: branch_mean_reward
dtype: float64
- name: gemini_summary_of_future
dtype: string
- name: index
dtype: int64
- name: row_id
dtype: int64
- name: prefix_len
dtype: int64
splits:
- name: train
num_bytes: 30858863
num_examples: 42
download_size: 29962741
dataset_size: 30858863
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
提供机构：
haoranli-ml
