search

mbzuai-oryx / VideoGPT-plus

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
Creative Commons Attribution 4.0 International
222 stars 15 forks source link

Question about Training Time #14

Open Backdrop9019 opened 4 months ago

Backdrop9019 commented 4 months ago

Hello,

Thank you for sharing your excellent research and code. I am currently pretraining an image encoder using 8 A100 GPUs. The estimated time of arrival (ETA) is about 6 hours. Is this normal? Could you share the pretraining and fine-tuning times along with the number of GPUs used for each setting? It would be very helpful.

Thank you!

Backdrop9019 commented 4 months ago

I also want to reproduce using vicuna-7b. Do I only need to modify the script to "BASE_LLM_PATH=lmsys/vicuna-7b-v1.5"? Or are there additional settings or hyperparameters that need to be changed?