Stabilizing Training with Small Batch Sizes using Exponential Moving Average (EMA)

[Franklalalala]

Background

Small batch sizes are commonly used in Hamiltonian AI training, as seen in the universal DeepH. However, this approach can lead to violent updates of model parameters.

Specific Observation (DeepTB on QH9 Dataset with Batch Size=1):

Describe the solution you'd like

Address the existing TODO regarding EMA implementation to ensure consistent training behavior across related projects.

Additional Context

This approach is already integrated into QHNet as a default setting.