Fine-tuning video captions

Thanks for your great work!
I', trying to ,modify the image training code to video captioning fine tuning, but there are somethings that doesn't quite clear to me how to modify like using "answer" parameter in MPLUG model.
Could you please release a train framework for this task?

I'm using `vatex_video_caps_dataset` class to load my dataset.

Thanks!

Start by locating the image training code, the MPLUG model handling of the "answer" parameter, and the vatex_video_caps_dataset class. Compare the existing dataset and training paths to determine the missing video-caption fine-tuning pieces. Done means a documented, usable training framework for this task, including the required parameter handling.

Written by the indexing model from the issue text.