Comments (6)
The major parameters to tune are the cutoff radii, which are 8 A and 4 A in the default setting. You can try a few combinations:
- your original ones 5 A, 5A
- the default ones: 8 A, 4 A
- perhap you can try another set: 7 A, 5 A
Then you can decide which to take based on accuarcy and speed
from gpumd.
from gpumd.
@brucefan1983
I was able to get smaller F-test errors with the default settings.
Is there a way to improve further with custom settings and perhaps including ZBL?
Thank you
Input or default parameters:
(default) model_type = potential.
(default) calculation mode = train.
(default) use NEP version 4.
(input) number of atom types = 5.
(default) type 0 (Hf with Z = 72) has force weight of 1.
(default) type 1 (O with Z = 8) has force weight of 1.
(default) type 2 (Si with Z = 14) has force weight of 1.
(default) type 3 (W with Z = 74) has force weight of 1.
(default) type 4 (Zr with Z = 40) has force weight of 1.
(default) will not add the ZBL potential.
(default) radial cutoff = 8 A.
(default) angular cutoff = 4 A.
(default) n_max_radial = 4.
(default) n_max_angular = 4.
(default) basis_size_radial = 12.
(default) basis_size_angular = 12.
(default) l_max_3body = 4.
(default) l_max_4body = 2.
(default) l_max_5body = 0.
(default) number of neurons = 30.
(default) lambda_1 = -1.
(default) lambda_2 = -1.
(default) lambda_e = 1.
(default) lambda_f = 1.
(default) lambda_v = 0.1.
(default) lambda_shear = 1.
(default) force_delta = 0.
(default) batch size = 1000.
(default) population size = 50.
(default) maximum number of generations = 100000.
Some calculated parameters:
number of radial descriptor components = 5.
number of angular descriptor components = 25.
total number of descriptor components = 30.
NN architecture = 30-30-1.
number of NN parameters to be optimized = 4801.
number of descriptor parameters to be optimized = 3250.
total number of parameters to be optimized = 8051.
from gpumd.
if you do not study radiation damage, there is no need to add ZBL.
When you need to add ZBL, it is usually required to have some dimer structures to make the connection between NEP and ZBL fixed.
from gpumd.
Actually, the defult regularization might be too strong. I have revised the default regularization a few days ago (#541), and you can try to see if that gives better training and testing accuracy.
from gpumd.
I think there is no real issue here, so I will close it.
from gpumd.
Related Issues (20)
- Cell info in netcdf output HOT 4
- Output six stress tensors in the dump_exyz file HOT 1
- AEMD HOT 9
- dump_observer average integration test failing HOT 8
- Implement SNES in GPU
- Header needs update in the dipole moment example file HOT 6
- full batch for energy training HOT 2
- cutoff distance in NEP.txt files HOT 4
- ensemble npt and F_e HOT 4
- nep executable error - "no kernel image is available for execution on the device" HOT 10
- units of input stress in trian.xyz/test.xyz HOT 2
- cudaErrorIllegalAddress: an illegal memory access was encountered HOT 8
- add force due to external electric field HOT 1
- Generate seperate frames by dump_exyz HOT 1
- trajectory file "dump.xyz" fails to include initial model.xyz as a start. HOT 1
- The keyword "velocity" in "run.in" to initialize the velocities of the system atoms might be given a reference value by default. HOT 1
- Possible BUG of enhance sampling perfomed by gpumd+plumed HOT 4
- Questions about NEP descriptors,Why is there an extra factor(2) in the derivation? HOT 5
- Add output for stopping_power_loss in electron_stop HOT 1
- A BUG of compute_rdf HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gpumd.