ML LFAST: Difference between revisions
No edit summary |
No edit summary |
||
| Line 10: | Line 10: | ||
To retrain the force field set the following: | To retrain the force field set the following: | ||
*{{TAG|ML_MODE}}=REFIT | *{{TAG|ML_MODE}}=REFIT | ||
or | or | ||
*{{TAG|ML_LFAST}}=.TRUE. | *{{TAG|ML_LFAST}}=.TRUE. | ||
*{{TAG|ML_ISTART}}=4 | *{{TAG|ML_ISTART}}=4 | ||
Revision as of 14:21, 11 January 2023
ML_LFAST = [logical]
Default: ML_LFAST = .FALSE.
Description: This tag switches on the descriptors for refitting for the very fast execution mode within machine learning force fields.
This tag is only available in the development version of VASP.
This tag switches on the descriptors for the very fast execution mode. The force field first has to be refit with the fast descriptors. As usual, the resulting {{TAG|ML_FFN} has to be copied to ML_FF and the fast code will be automatically run in production mode runs bey setting (ML_MODE=RUN or ML_ISTART=2).
To retrain the force field set the following:
- ML_MODE=REFIT
or
The speedup of the fast method compared to the regular method is increasing with increasing number of local reference configurations.
It should be noted that in the fast version no Bayesian error estimation is available.
Since the calculation time of the fast version is of the same order of magnitude as the timing for the output of the molecular-dynamics results, we advise decreasing the output frequency for molecular dynamics. This is controlled by the tag ML_OUTBLOCK. By default, it writes out all molecular-dynamics results at every molecular-dynamics step. Additionally, the calculation and output of the pair-correlation function is suppressed by ML_OUTPUT_MODE=0 as default.
Related tags and articles
ML_LMLFF, ML_ISTART, ML_IERR, ML_OUTBLOCK, ML_OUTPUT_MODE