Energies from single points vs. AIMD for training Machine Learning Force Fields

I am currently training a force field using machine learning techniques. One way to test the performance of the ML model is to use the force field for a production run (= molecular dynamics) and taking snapshots. For each snapshot a single point calculation (=DFT) should be performed. Then energies, forces and stresses are compared from single-point calculation and the MD run.The MD run is at finite temperature and I think this has an impact on the total energy of the system. However, single point calculations are at zero temperature.
How to compare the total energies then?Maybe I miss a point about single point calculations. I am doing them in VASP by setting IBRION = -1 , NSW = 0 . I think a temperature cannot be set up for a single point calculation?