problems when running MD simulation by using ML_FF

[suojiang_zhang1]

Hi,
I got a ML_FF with rmse_energy=0.0242 and rmse_force=0.134 with 6 molecules in a box, the initial density is smaller than experimental density. When the box is extended by *2 in XYZ directions, I ran a MD simulation by using the trained FF, copy ML_FFN to ML_FF, and ML_ISTART=2, I found that the positions of atoms were almost not changed in 1ps simulation.
I increased the temperature from 300 to 400, the change is not obvious.
please give me some advices.

[martin.schlipf]

Could you provide a full report, please?

Provide a report in form of a zip-file in the attachment of your post that contains:

• all input files of the job, that is POSCAR, INCAR, KPOINTS, POTCAR
• OUTCAR and stdout of the run
• your jobscript, if you use one

Please note that zip files smaller than 8 MB are accepted only.