Update pytorch-lightning (#263)

* model version for Potential class is added

* model version for Potential class is modified

* Enable the smooth version of Spherical Bessel function in TensorNet

* max_n, max_l for SphericalBessel radial basis functions are included in TensorNet class

* adding united tests for improving the coverage score

* little clean up in _so3.py and so3.py

* remove unnecessary data storage in dgl graphs

* update pymatgen version to fix the bug

* refractor all include_states into include_state for consistency

* change include_states into include_state in test_graph_conv.py

* Ensure the state attr from molecule graph is consistent with matgl.float_th and including linear layer in TensorNet to match the original implementations

* Fix the jupyter-notebook for M3GNet training

* included more united tests to improve code coverage

* update pyproject.toml and requirements.txt to adapt dgl-2.x

* downgrade dgl to 2.1.0

* Improve more code coverage in _chgnet.py

* update pytorch-lightning

requirements.txt

@@ -1,6 +1,6 @@
 dgl==2.1.0
 torch==2.2.1
-pytorch_lightning==2.0.9
+pytorch_lightning==2.0.9.post0
 pymatgen==2024.3.1
 ase==3.22.1
 pydantic==2.7.1