kuleshov-group / caduceus

Bi-Directional Equivariant Long-Range DNA Sequence Modeling
Apache License 2.0
137 stars 14 forks source link

runtime terminal behaves #33

Closed yongrenr closed 1 month ago

yongrenr commented 1 month ago

Hello! I think your work is very detailed! I ran your code! Since I'm not familiar with pytorch-lightning, I'm curious about how the runtime terminal behaves. image

yair-schiff commented 1 month ago

This progress bar is create by lightning. The progress is a combination of train and validation epochs. Loss is the training loss in this case. Please let me know if that answers your question

yongrenr commented 1 month ago

This progress bar was created by lightning. Progress is a combination of training and validation periods. In this case, the loss is the loss of training. Please let me know if this answers your question

If I want to add something else to show in it, do you know any way to modify it?

yair-schiff commented 1 month ago

I don't know all the full functionality here but this link might help.

When you make self.log calls in the trainer there is a parameter called prog_bar, set it to True to add whatever metric / value you want to display in the progress bar, e.g. here