I am trying to do a video classification project by using 3DCNN and I plotted the loss curves & accuracy curves. I have some questions. i'm using kfold Cross validation. Should i save the parameters after every fold and choose the best one? how to reduce the loss? is it overfitting? one of the fold loss accuracy another fold accuracy loss

Is it overfitting?

I am trying to do a video classification project by using 3DCNN and I plotted the loss curves & accuracy curves. I have some questions.

i'm using kfold Cross validation. Should i save the parameters after every fold and choose the best one?
how to reduce the loss?
is it overfitting?

one of the fold

another fold