mPLUG-Owl icon indicating copy to clipboard operation
mPLUG-Owl copied to clipboard

多模态和单模态数据的混合方式

Open JustQJ opened this issue 1 year ago • 1 comments

论文中提到了第二阶段的微调使用了多模态(llava)和单模态数据(alpaca, vicuna, baize),想问一下这两种数据是混在一起训练的还是单独分开训练的。如果是混在一起,那么每个batch中的单模态和多模态数据的比例是怎么确定的。 谢谢!

JustQJ avatar Aug 26 '23 13:08 JustQJ

We random mix the text data and multi-modal data. For each batch, we do not control the ratio, it just random sampled, and the ratio within a batch would similar to the ratio within the dataset.

MAGAer13 avatar Aug 30 '23 09:08 MAGAer13