zjhhhh/iter2_7b_multi_adversary_mean_beta_1.0_multi_expand_tokenized
收藏Hugging Face2025-11-25 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/zjhhhh/iter2_7b_multi_adversary_mean_beta_1.0_multi_expand_tokenized
下载链接
链接失效反馈官方服务:
资源简介:
---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: prompt
dtype: string
- name: requirements
dtype: string
- name: selection_response_1
dtype: string
- name: selection_response_2
dtype: string
- name: selection_response_3
dtype: string
- name: selection_response_4
dtype: string
- name: current_response_1
dtype: string
- name: current_response_2
dtype: string
- name: adversary_response_1
dtype: string
- name: adversary_response_2
dtype: string
- name: base_response_1
dtype: string
- name: base_response_2
dtype: string
- name: selection_1_adversary_1_mean
list: float64
- name: selection_1_adversary_1_majority
list: float64
- name: selection_1_adversary_2_mean
list: float64
- name: selection_1_adversary_2_majority
list: float64
- name: selection_2_adversary_1_mean
list: float64
- name: selection_2_adversary_1_majority
list: float64
- name: selection_2_adversary_2_mean
list: float64
- name: selection_2_adversary_2_majority
list: float64
- name: selection_3_adversary_1_mean
list: float64
- name: selection_3_adversary_1_majority
list: float64
- name: selection_3_adversary_2_mean
list: float64
- name: selection_3_adversary_2_majority
list: float64
- name: selection_4_adversary_1_mean
list: float64
- name: selection_4_adversary_1_majority
list: float64
- name: selection_4_adversary_2_mean
list: float64
- name: selection_4_adversary_2_majority
list: float64
- name: current_1_adversary_1_mean
list: float64
- name: current_1_adversary_1_majority
list: float64
- name: current_1_adversary_2_mean
list: float64
- name: current_1_adversary_2_majority
list: float64
- name: current_2_adversary_1_mean
list: float64
- name: current_2_adversary_1_majority
list: float64
- name: current_2_adversary_2_mean
list: float64
- name: current_2_adversary_2_majority
list: float64
- name: qwen_prompt
dtype: string
- name: qwen_prompt_tokens
list: int64
- name: chosen
dtype: string
- name: reject
dtype: string
- name: qwen_chosen
dtype: string
- name: qwen_reject
dtype: string
- name: qwen_chosen_tokens
list: int64
- name: qwen_reject_tokens
list: int64
- name: chosen_reward
dtype: float64
- name: reject_reward
dtype: float64
- name: g_chosen
dtype: float64
- name: g_reject
dtype: float64
- name: j_star
dtype: int64
splits:
- name: train
num_bytes: 25778429133
num_examples: 243773
- name: test
num_bytes: 75335965
num_examples: 720
download_size: 2335621708
dataset_size: 25853765098
---
提供机构:
zjhhhh



