Error when specifying more e0s then present in training set

[LarsSchaaf]

Description
When you specify e0s for Oxygen for example, but you dont have any oxygen in your training set you get the following error:

 File "programms/mace/modules/blocks.py", line 160, in forward
    return torch.matmul(x, torch.atleast_2d(self.atomic_energies).T)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (799x7 and 8x1)

To Reproduce
Specify e0s from input script of two elements, but only have one element in dataset
--E0s={1:0.1, 2:0.2}

Solution:
Edit:

mace/mace/cli/run_train.py

Line 405 in 158b1f2

logging.info(f"Atomic Energies used (z: eV) for head {head_config.head_name}: " + "{" + ", ".join([f"{z}: {atomic_energies_dict[head_config.head_name][z]}" for z in head_config.z_table.zs]) + "}")

[gabor1]

Hm.. I guess we could just silently ignore additional E0s.