Does eval loss decreasing slower than train loss indicate overfitting?

I am training a binary classifier using an efficientnetv2 model with a 1M image dataset where I do a 60/20/20 split. Does this graph mean that the model is over-fitting? I can see that the train loss is going down much faster than the eval loss but the eval loss is still going down and the accuracy is going up.

Accuracy may seem to be low but it is actually a pretty decent amount for the problem I am working with.