ML MCONF NEW: Difference between revisions
(Documented that increasing the parameter for ML_ISTART=3 increases efficiency.) |
No edit summary |
||
| Line 7: | Line 7: | ||
The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations|here]]. | The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Sampling of training data and local reference configurations|here]]. | ||
If force fields are reparameterized ({{TAG|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased. | If force fields are reparameterized ({{TAG|ML_ISTART}}=3), calculations are usually more efficient, if this parameter is increased to values around 10-16 in particular, if the ML_AB files are large. | ||
== Related tags and articles == | == Related tags and articles == | ||
Revision as of 08:42, 26 August 2022
ML_MCONF_NEW = [integer]
Default: ML_MCONF_NEW = 5
Description: This tag sets the number of configurations that are stored temporarily as candidates for the training data in the machine learning force field method.
| Warning: This value is close to optimal for on-the-fly learning, and should usually not be changed. |
The use of this tag in combination with the learning algorithms is described here: here. If force fields are reparameterized (ML_ISTART=3), calculations are usually more efficient, if this parameter is increased to values around 10-16 in particular, if the ML_AB files are large.