ML MCONF - Revision history

Karsai at 09:22, 28 April 2023

2023-04-28T09:22:34Z

← Older revision		Revision as of 09:22, 28 April 2023
Line 6:		Line 6:
	The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:		The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:
	*{{TAG\|ML_MODE}}='TRAIN':		*{{TAG\|ML_MODE}}='TRAIN':
	**No {{TAG\|ML_AB}} present (learning from scratch): ~~<math>\quad</math>~~ min(1500, max(1,{{TAG\|NSW}}))		**No {{TAG\|ML_AB}} present (learning from scratch): min(1500, max(1,{{TAG\|NSW}}))
	**{{TAG\|ML_AB}} present (continuation of learning): ~~<math>\quad</math>~~ MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))		**{{TAG\|ML_AB}} present (continuation of learning): MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))
	*{{TAG\|ML_MODE}}='SELECT': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='SELECT': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='REFIT': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='REFIT': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='REFITBAYESIAN': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='REFITBAYESIAN': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='RUN': ~~<math>\quad</math>~~ 1		*{{TAG\|ML_MODE}}='RUN': 1
	using the following definition:		using the following definition:
	*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.		*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.

Karsai at 09:03, 28 April 2023

2023-04-28T09:03:17Z

← Older revision		Revision as of 09:03, 28 April 2023
Line 1:		Line 1:
	{{DISPLAYTITLE:ML_MCONF}}		{{DISPLAYTITLE:ML_MCONF}}
	{{TAGDEF\|ML_MCONF\|[integer]\|~~1500~~}}		{{TAGDEF\|ML_MCONF\|[integer]\|see below}}

	Description: This tag sets the maximum number of structures stored in memory ~~which~~ are used for training in the machine learning force field method.		Description: This tag sets the maximum number of structures stored in memory that are used for training in the machine learning force field method.
	----		----
	The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.		The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:
	This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.		*{{TAG\|ML_MODE}}='TRAIN':
			**No {{TAG\|ML_AB}} present (learning from scratch): <math>\quad</math> min(1500, max(1,{{TAG\|NSW}}))
			**{{TAG\|ML_AB}} present (continuation of learning): <math>\quad</math> MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))
			*{{TAG\|ML_MODE}}='SELECT': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='REFIT': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='REFITBAYESIAN': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='RUN': <math>\quad</math> 1
			using the following definition:
			*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.


			The default value for {{TAG\|ML_MODE}}=''TRAIN'' is usually a safe value for solids and easy-to-learn liquids but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.

			This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code.

			An estimate of the design matrix and all other large arrays are printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

	== Related tags and articles ==		== Related tags and articles ==

Huebsch at 09:03, 25 May 2022

2022-05-25T09:03:12Z

← Older revision		Revision as of 09:03, 25 May 2022
Line 13:		Line 13:
	{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}		{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}

	[[Category:INCAR tag]][[Category:Machine-learned force fields]]		[[Category:INCAR tag]][[Category:Machine-learned force fields]][[Category:Memory]]

Karsai: /* Related tags and articles */

2022-04-08T13:27:37Z

Karsai at 07:34, 7 April 2022

2022-04-07T07:34:27Z

← Older revision		Revision as of 07:34, 7 April 2022
Line 1:		Line 1:
			{{DISPLAYTITLE:ML_MCONF}}
	{{TAGDEF\|ML_MCONF\|[integer]\|1500}}		{{TAGDEF\|ML_MCONF\|[integer]\|1500}}

Line 6:		Line 7:
	This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.		This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

	== Related ~~Tags~~ and ~~Sections~~ ==		== Related tags and articles ==

	{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}		{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}
Line 12:		Line 13:
	{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}		{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}

	[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields~~]][[Category: Alpha~~]]		[[Category:INCAR tag]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]]

Singraber: TODO: Improve!

2021-10-11T21:26:14Z

TODO: Improve!

← Older revision		Revision as of 21:26, 11 October 2021
Line 1:		Line 1:
	{{TAGDEF\|ML_MCONF\|[integer]\|1500}}		{{TAGDEF\|ML_MCONF\|[integer]\|1500}}

	Description: This ~~flag~~ sets the maximum number of structures used for training in the machine learning force field method.		Description: This tag sets the maximum number of structures stored in memory which are used for training in the machine learning force field method.
	----		----
	The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.		The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.
	This flag sets ~~alse~~ the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.		This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

	== Related Tags and Sections ==		== Related Tags and Sections ==

Karsai at 08:59, 23 August 2021

2021-08-23T08:59:45Z

← Older revision		Revision as of 08:59, 23 August 2021
Line 1:		Line 1:
	{{TAGDEF\|~~ML_FF_MCONF~~\|[integer]\|1500}}		{{TAGDEF\|ML_MCONF\|[integer]\|1500}}

	Description: This flag sets the maximum number of structures used for training in the machine learning force field method.		Description: This flag sets the maximum number of structures used for training in the machine learning force field method.
	----		----
	The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|~~ML_FF_MCONF~~}}.		The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.
	This flag sets alse the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.		This flag sets alse the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

Line 10:		Line 10:
	{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}		{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}
	----		----
	{{TAG\|~~ML_FF_LMLFF~~}}, {{TAG\|~~ML_FF_MCONF_NEW~~}}, {{TAG\|~~ML_FF_MB_MB~~}}		{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}

	[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]		[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]

Karsai: Karsai moved page ML FF MCONF to ML MCONF

2021-08-23T06:45:16Z

Karsai moved page ML FF MCONF to ML MCONF

← Older revision	Revision as of 06:45, 23 August 2021
(No difference)

Karsai at 09:49, 8 June 2021

2021-06-08T09:49:04Z

← Older revision		Revision as of 09:49, 8 June 2021
Line 3:		Line 3:
	Description: This flag sets the maximum number of structures used for training in the machine learning force field method.		Description: This flag sets the maximum number of structures used for training in the machine learning force field method.
	----		----
	~~In most cases the~~ default value ~~of 1000~~ should be ~~sufficient and hence not touched. Only if the number of training~~ set ~~has~~ reached ~~1000 in~~ the {{TAG\|~~ML_AB~~}} ~~or (~~{{TAG\|~~ML_ABN~~}}~~) file (look~~ for the ~~line ''The~~ number of ~~configurations'') this value should be set higher. If such thing occurs also the last training step should be repeated~~.		The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_FF_MCONF}}.
			This flag sets alse the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

	== Related Tags and Sections ==		== Related Tags and Sections ==
Line 9:		Line 10:
	{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}		{{sc\|ML_FF_MCONF\|Examples\|Examples that use this tag}}
	----		----
	{{TAG\|ML_FF_LMLFF}},{{TAG\|ML_FF_MCONF_NEW}}		{{TAG\|ML_FF_LMLFF}}, {{TAG\|ML_FF_MCONF_NEW}}, {{TAG\|ML_FF_MB_MB}}

	[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]		[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]][[Category: Alpha]]

Karsai at 13:42, 17 March 2021

2021-03-17T13:42:25Z

← Older revision		Revision as of 13:42, 17 March 2021
Line 1:		Line 1:
	{{TAGDEF\|ML_FF_MCONF\|[integer]\|~~1000~~}}		{{TAGDEF\|ML_FF_MCONF\|[integer]\|1500}}

	Description: This flag sets the maximum number of structures used for training in the machine learning force field method.		Description: This flag sets the maximum number of structures used for training in the machine learning force field method.

← Older revision		Revision as of 09:22, 28 April 2023
Line 6:		Line 6:
	The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:		The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:
	*{{TAG\|ML_MODE}}='TRAIN':		*{{TAG\|ML_MODE}}='TRAIN':
	**No {{TAG\|ML_AB}} present (learning from scratch): ~~<math>\quad</math>~~ min(1500, max(1,{{TAG\|NSW}}))		**No {{TAG\|ML_AB}} present (learning from scratch): min(1500, max(1,{{TAG\|NSW}}))
	**{{TAG\|ML_AB}} present (continuation of learning): ~~<math>\quad</math>~~ MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))		**{{TAG\|ML_AB}} present (continuation of learning): MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))
	*{{TAG\|ML_MODE}}='SELECT': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='SELECT': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='REFIT': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='REFIT': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='REFITBAYESIAN': ~~<math>\quad</math>~~ MCONF_AB + 1		*{{TAG\|ML_MODE}}='REFITBAYESIAN': MCONF_AB + 1
	*{{TAG\|ML_MODE}}='RUN': ~~<math>\quad</math>~~ 1		*{{TAG\|ML_MODE}}='RUN': 1
	using the following definition:		using the following definition:
	*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.		*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.

← Older revision		Revision as of 09:03, 28 April 2023
Line 1:		Line 1:
	{{DISPLAYTITLE:ML_MCONF}}		{{DISPLAYTITLE:ML_MCONF}}
	{{TAGDEF\|ML_MCONF\|[integer]\|~~1500~~}}		{{TAGDEF\|ML_MCONF\|[integer]\|see below}}

	Description: This tag sets the maximum number of structures stored in memory ~~which~~ are used for training in the machine learning force field method.		Description: This tag sets the maximum number of structures stored in memory that are used for training in the machine learning force field method.
	----		----
	The default value is usually a safe value but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.		The defaults for {{TAG\|ML_MCONF}} are different for each different {{TAG\|ML_MODE}} setting. Here are the defaults for each mode:
	This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program, since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code. An estimate of the design matrix and all other large arrays is printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.		*{{TAG\|ML_MODE}}='TRAIN':
			**No {{TAG\|ML_AB}} present (learning from scratch): <math>\quad</math> min(1500, max(1,{{TAG\|NSW}}))
			**{{TAG\|ML_AB}} present (continuation of learning): <math>\quad</math> MCONF_AB + min(1500, max(1,{{TAG\|NSW}}))
			*{{TAG\|ML_MODE}}='SELECT': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='REFIT': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='REFITBAYESIAN': <math>\quad</math> MCONF_AB + 1
			*{{TAG\|ML_MODE}}='RUN': <math>\quad</math> 1
			using the following definition:
			*MCONF_AB = Number of training structures read from the {{TAG\|ML_AB}} file.


			The default value for {{TAG\|ML_MODE}}=''TRAIN'' is usually a safe value for solids and easy-to-learn liquids but should be set to a higher value as soon as it is reached. When this happens the code stops and gives an error instructing to increase {{TAG\|ML_MCONF}}.

			This flag sets also the maximum number of rows for the design matrix, which is usually a huge matrix. The design matrix is to be allocated statically at the beginning of the program since several parts of the code use MPI shared memory and dynamic reallocation of these arrays can cause severe problems on some systems. So most of the main arrays are statically allocated in the code.

			An estimate of the design matrix and all other large arrays are printed out to the {{TAG\|ML_LOGFILE}} before allocation. The design matrix is fully distributed in a block cyclic fashion for scaLAPACK and should almost perfectly linearly scale with the number of used processors.

	== Related tags and articles ==		== Related tags and articles ==

← Older revision		Revision as of 13:27, 8 April 2022
Line 13:		Line 13:
	{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}		{{TAG\|ML_LMLFF}}, {{TAG\|ML_MCONF_NEW}}, {{TAG\|ML_MB}}

	[[Category:INCAR tag]][[Category:Machine ~~Learning]][[Category:Machine Learned Force Fields~~]]		[[Category:INCAR tag]][[Category:Machine-learned force fields]]