search

shikras / shikra

Other
710 stars 44 forks source link

Doubts about Training Commands: Inconsistency between the Ratio in the Two-Stage Training #24

Open Dongshengjiang opened 11 months ago

Dongshengjiang commented 11 months ago

Thank you for sharing the code and data. Could you please provide detailed training commands? According to the article, the training process consists of two stages: the first stage is the reorganized VL dataset, and the second stage is the instruction stage with a 5:5 sampling ratio. However, we noticed that the provided training command is only 'config/shikra_pretrain_final19_stage2', which has a ratio of 1:9. This is a bit confusing. Could you please clarify the correct training commands for both stages as mentioned in the article?

bohanzhaiTT commented 11 months ago

Any comments?

harrytea commented 9 months ago

same question