-
Module Optimization
Enhanced performance by optimizing several modules, resulting in more efficient and faster execution. -
Refactored Forward and Loss Calculation Logic
Moved the forward and loss calculation logic from Lightning modules to functional modules.
This change improves modularity and maintainability of the codebase. -
Code Refactoring
Refactored the overall codebase for better readability, and maintainability. -
New Freeze Encoder Flag
Added a freeze_encoder flag to the set_second_phase method. This flag allows users to easily freeze or unfreeze the encoder during the second phase of training, providing greater flexibility in model training.