CV MSE almost equals Test MSE, but Train MSE = 0, is it an overfitting problem?

Question

I am training a decisoin tree model and i got the (see picture) as results, so basically i am a bit confused about the result.

Given it's a school project, so i am training a model based on 969 lines only and 18 features, and without any feature engineering.

Thank you in advance for your response.

Answer 1

there is no overfitting since you got a test score almost equals CV score. However try to reproduce your system with random train/dev/test sets to assure that you get the same results