Error in Fine Tunning

[Harpriyaminhas]

I am facing problem in fine tuning using MD dataset.

1. I am able to convert the VASP output to "CHGNet_structures.json; CHGNet_structures.p; CIF_Files/ ; Graph_Files/ . "
2. I am getting the results for
   

But when it comes to training, it is showing below mentioned error.
"Traceback (most recent call last):
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/chgnet/data/dataset.py", line 166, in getitem
"e": torch.tensor(self.energies[graph_id], dtype=datatype),
TypeError: must be real number, not NoneType

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/chgnet/data/dataset.py", line 162, in getitem
crystal_graph = self.graph_converter(
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/chgnet/graph/converter.py", line 185, in forward
composition=structure.composition.formula,
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/pymatgen/core/structure.py", line 421, in composition
return Composition(elem_map)
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/site-packages/pymatgen/core/composition.py", line 128, in init
if len(args) == 1 and isinstance(args[0], type(self)):
File "/apps/conda_env/anaconda3-2022/envs/chgnet/lib/python3.9/abc.py", line 119, in instancecheck
return _abc_instancecheck(cls, instance)
RecursionError: maximum recursion depth exceeded in comparison

During handling of the above exception, another exception occurred:"
error.zip

Please help me to resolve above error
Thank You