--------------------------------------------------------------------------
By default, for Open MPI 4.0 and later, infiniband ports on a device
are not used by default.  The intent is to use UCX for these devices.
You can override this policy by setting the btl_openib_allow_ib MCA parameter
to true.

  Local host:              c004
  Local adapter:           mlx5_0
  Local port:              1

--------------------------------------------------------------------------
--------------------------------------------------------------------------
WARNING: There was an error initializing an OpenFabrics device.

  Local host:   c004
  Local device: mlx5_0
--------------------------------------------------------------------------
Exception: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
  File "code/__torch__.py", line 16, in forward
    contributions: Tensor) -> Tuple[Tensor, Optional[Tensor]]:
    model = self.model
    _0 = (model).forward(species, coords, edge_index0, edge_index1, edge_index2, contributions, )
          ~~~~~~~~~~~~~~ <--- HERE
    E, F, = _0
    n_atoms = torch.sum(torch.sub(contributions, 1))
  File "code/__torch__/mace/modules/models.py", line 31, in batch_norm
    num_graphs = torch.numel(n_contributing)
    num_elements = self.num_elements
    node_attr = torch.one_hot(x, annotate(int, num_elements))
                ~~~~~~~~~~~~~ <--- HERE
    _2 = torch.to(node_attr, ops.prim.dtype(pos))
    node_attr0 = torch.to(_2, ops.prim.device(pos))

Traceback of TorchScript, original code (most recent call last):
  File "<ipython-input-6-fa77f58fbe83>", line 40, in forward
    def forward(self, species, coords, edge_index0, edge_index1, edge_index2, contributions):
        E, F = self.model(species, coords, edge_index0, edge_index1, edge_index2, contributions)
               ~~~~~~~~~~ <--- HERE
        n_atoms = torch.sum(contributions - 1)
        E = E + self.si_ref * n_atoms
  File "/home/amit/Projects/COLABFIT/mace/mace/mace/modules/models.py", line 195, in batch_norm
        num_graphs = n_contributing.numel()
    
        node_attr = torch.nn.functional.one_hot(x, num_classes=self.num_elements)
                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
        node_attr = node_attr.to(pos.dtype).to(pos.device)
        node_attr.requires_grad_(True)
RuntimeError: Class values must be smaller than num_classes.

--------------------------------------------------------------------------
MPI_ABORT was invoked on rank 0 in communicator MPI_COMM_WORLD
with errorcode 1.

NOTE: invoking MPI_ABORT causes Open MPI to kill all MPI processes.
You may or may not see output from other processes, depending on
exactly when Open MPI kills them.
--------------------------------------------------------------------------
Traceback (most recent call last):
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 46, in run_lammps
    lammps_process = subprocess.check_call(
  File "/usr/lib/python3.8/subprocess.py", line 364, in check_call
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['lammps', '-in', 'isolated_atom.lammps.Si.in']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 217, in <module>
    isolated_atom_energies[symbol] = get_isolated_atom_energy(
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 72, in get_isolated_atom_energy
    run_lammps(templated_input, lammps_output)
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 56, in run_lammps
    raise Exception("LAMMPS did not exit properly:\n" + extrainfo)
Exception: LAMMPS did not exit properly:
LAMMPS (2 Aug 2023 - Update 1)

Command exited with non-zero status 1

{"realtime":3.54,"usertime":3.55,"systime":6.59,"memmax":324020,"memavg":0}