-
Notifications
You must be signed in to change notification settings - Fork 51
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I get a problem with loss=0 in 3_train progess #67
Comments
No. You can post the standard output of your training process, and then we’ll see what’s going on. |
stpe 1: openmx.std is the no.100 file standard output, |
I transferred the file but couldn't see the attachment. I'll make a new copy of openmx.std, which is the No.100 file standard output: The number of threads in each node for OpenMP parallelization is 1. Welcome to OpenMX Ver. 3.9.9 Automatic determination of Kerker_factor: 4.630342780814 <Input_std> Your input file was normally read.
<SetPara_DFT> PAOs of species Bi were normally found.
<FT_PAO> Fourier transform of pseudo atomic orbitals Allocation of atoms to processors at MD_iter= 1 proc = 0 # of atoms= 3 estimated weight= 3.00000
TFNAN= 1434 Average FNAN= 39.83333 TFNAN= 1434 Average FNAN= 39.83333 TFNAN= 1434 Average FNAN= 39.83333 <Check_System> The system is slab.
<MD= 1> Calculation of the overlap matrix ******************* MD= 1 SCF= 1 ******************* Sum of MulP: up = 270.10116 down = 269.89884 ******************* MD= 1 SCF= 2 ******************* Sum of MulP: up = 270.10116 down = 269.89884 ******************* MD= 1 SCF= 3 ******************* Sum of MulP: up = 270.10140 down = 269.89860 ******************* MD= 1 SCF= 4 ******************* Sum of MulP: up = 270.10373 down = 269.89627 ******************* MD= 1 SCF= 5 ******************* Sum of MulP: up = 270.10490 down = 269.89510 ******************* MD= 1 SCF= 6 ******************* Sum of MulP: up = 270.10538 down = 269.89462 ******************* MD= 1 SCF= 7 ******************* Sum of MulP: up = 270.10552 down = 269.89448 ******************* MD= 1 SCF= 8 ******************* Sum of MulP: up = 270.10584 down = 269.89416 ******************* MD= 1 SCF= 9 ******************* Sum of MulP: up = 270.10552 down = 269.89448 ******************* MD= 1 SCF=10 ******************* Sum of MulP: up = 270.10569 down = 269.89431 ******************* MD= 1 SCF=11 ******************* Sum of MulP: up = 270.10575 down = 269.89425 ******************* MD= 1 SCF=12 ******************* Sum of MulP: up = 270.10565 down = 269.89435 ******************* MD= 1 SCF=13 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=14 ******************* Sum of MulP: up = 270.10565 down = 269.89435 ******************* MD= 1 SCF=15 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=16 ******************* Sum of MulP: up = 270.10565 down = 269.89435 ******************* MD= 1 SCF=17 ******************* Sum of MulP: up = 270.10565 down = 269.89435 ******************* MD= 1 SCF=18 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=19 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=20 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=21 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=22 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=23 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=24 ******************* Sum of MulP: up = 270.10566 down = 269.89434 ******************* MD= 1 SCF=25 ******************* Sum of MulP: up = 270.10566 down = 269.89434
Absolute D 1444.89956958
Total -1437.61595135 -144.89697655 0.09381759
Uele = -410.898722276364 Ukin = 1415.790018586999 UpV = 0.000000000000 Uele: band energy
DFT in total = 944.47274 Set_OLP_Kin = 1.48868 The SCF was achieved at MD= 1
outputting data on grids to files... Save the scfout file (.//openmx.scfout)
Total Computational Time = 3 964.998 0 965.005 *** In DFT *** Set_OLP_Kin = 3 1.408 4 2.133 The calculation was normally finished. |
I have completed both the 1DFT_calculation and the 2reprocess, and now I am encountering a loss=0 situation during 3_train training. I am sure that the logs for the first two steps are both finished and have data. The first step takes too long time,I would like to conduct a small batch test for 3_train. Neither I train 10 or train 100 folders with the same result loss=0, do I have to process all the data in folders 0-575 before I can proceed with 3_train?
The text was updated successfully, but these errors were encountered: