I am currently working with some models aimed at predicting time series (89 days for training, 22 for testing), including a CNN LSTM and a convLSTM.
When training these models, I had the following scenario:
In the first case, it is possible to see the val loss moving more sharply away from the train loss. In the second case, it seems to me that this also happens, but in a much smoother way.
What do these graphs mean? What causes these situations to occur? If they are problematic situations, is it possible to correct them? If so, how?