jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-margin
收藏Hugging Face2026-04-27 更新2026-05-03 收录
下载链接:
https://hf-mirror.com/datasets/jackf857/qwen3-8b-base-beta-dpo-hh-helpful-4xh200-margin
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: epoch
dtype: float64
- name: step
dtype: int64
- name: batch_size
dtype: int64
- name: mean
dtype: float64
- name: std
dtype: float64
- name: min
dtype: float64
- name: p10
dtype: float64
- name: median
dtype: float64
- name: p90
dtype: float64
- name: max
dtype: float64
- name: pos_frac
dtype: float64
- name: sample
sequence: float64
- name: npy
dtype: string
splits:
- name: train
num_bytes: 471252
num_examples: 681
download_size: 391012
dataset_size: 471252
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
提供机构:
jackf857



