pair_nequip error

lammps.log

LAMMPS (29 Sep 2021 - Update 2)
Reading data file ...
  orthogonal box = (0.0000000 0.0000000 0.0000000) to (35.000000 35.000000 35.000000)
  1 by 1 by 1 MPI processor grid
  reading atoms ...
  489 atoms
  read_data CPU = 0.001 seconds
NEQUIP is using device cuda
NequIP Coeff: type 1 is element Pt
Loading model from pt_potential.pth
Freezing TorchScript model...
WARNING: Using 'neigh_modify every 1 delay 0 check yes' setting during minimization (src/lammps/src/min.cpp:188)
Neighbor list info ...
  update every 1 steps, delay 0 steps, check yes
  max neighbors/atom: 2000, page size: 100000
  master list distance cutoff = 7
  ghost atom cutoff = 7
  binsize = 3.5, bins = 10 10 10
  1 neighbor lists, perpetual/occasional/extra = 1 0 0
  (1) pair nequip, perpetual
      attributes: full, newton off
      pair build: full/bin/atomonly
      stencil: full/bin/3d
      bin: standard
Setting up cg style minimization ...
  Unit style    : metal
  Current step  : 0
Per MPI rank memory allocation (min/avg/max) = 4.184 | 4.184 | 4.184 Mbytes
Step Temp E_pair E_mol TotEng Press
       0            0   -2503.5989            0   -2503.5989            0
      76            0   -2010459.9            0   -2010459.9            0
Loop time of 153.489 on 1 procs for 76 steps with 489 atoms

117.8% CPU use with 1 MPI tasks x no OpenMP threads

Minimization stats:
  Stopping criterion = energy tolerance
  Energy initial, next-to-last, final =
     -2503.59887695312       -2010453.375       -2010459.875
  Force two-norm initial, final = 97.727561 65634808.0
  Force max component initial, final = 23.158852 44838200.0
  Final line search alpha, max atom move = 5.1057694e-13 2.2893351e-05
  Iterations, force evaluations = 76 318

MPI task timing breakdown:
Section |  min time  |  avg time  |  max time  |%varavg| %total
---------------------------------------------------------------
Pair    | 153.48     | 153.48     | 153.48     |   0.0 |100.00
Neigh   | 0.0015349  | 0.0015349  | 0.0015349  |   0.0 |  0.00
Comm    | 0.00023675 | 0.00023675 | 0.00023675 |   0.0 |  0.00
Output  | 0          | 0          | 0          |   0.0 |  0.00
Modify  | 0          | 0          | 0          |   0.0 |  0.00
Other   |            | 0.002545   |            |       |  0.00

Nlocal:        489.000 ave         489 max         489 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost:         0.00000 ave           0 max           0 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs:         0.00000 ave           0 max           0 min
Histogram: 1 0 0 0 0 0 0 0 0 0
FullNghs:      27926.0 ave       27926 max       27926 min
Histogram: 1 0 0 0 0 0 0 0 0 0

Total # of neighbors = 27926
Ave neighs/atom = 57.108384
Neighbor list builds = 2
Dangerous builds = 0
Setting up Verlet run ...
  Unit style    : metal
  Current step  : 76
  Time step     : 0.001
Per MPI rank memory allocation (min/avg/max) = 3.059 | 3.059 | 3.059 Mbytes
Step PotEng KinEng TotEng Temp Volume
      76     -2010460    48.760029   -2010411.2          773        42875
corrupted double-linked list
[1]    112200 abort (core dumped)  lmp_nequip -in system.in

system.in

units 		metal
dimension	3
boundary	f	f	f
atom_style	atomic
# ------------------------ FORCE FIELDS ------------------------------

read_data       pt.data
pair_style	nequip
pair_coeff	* * pt_potential.pth Pt
newton off on
######################################

minimize        1.0e-5 1.0e-5 1000 10000
min_style       cg

timestep 0.001
velocity all create 773.00 454883 mom yes rot yes dist gaussian

thermo  500
thermo_style    custom step pe ke etotal temp vol

fix 1 all nvt temp 773.00 773.00 1.0

dump 		1 all xyz 500 movie.xyz
dump_modify 1 element Pt

run		100000
unfix   1

fix 2 all nvt temp 773.00 303.00 1.0
dump       2 all xyz 500 movie2.xyz
dump_modify 2 element Pt

run     100000
unfix   2

fix 3 all nvt temp 303.00 303.00 1.0
dump       3 all xyz 500 movie3.xyz
dump_modify 3 element Pt

run     100000
unfix   3


write_data   output_npc3.data