Feature/model pruning

[BradleyEdelman]

This PR introduces a refined adaptive training strategy with a constant pruning ratio. Key updates:

• Score Calculation: This version now computes an accuracy score and a memory score based on resource usage and model performance
• Parameter Prioritization: Accuracy and memory scores are weighted according to default or user-defined priority weighting to idenfity a priority list for parameter adjustment. Now, only the top priority paramater is adjusted in each epoch.
  • Batch size priority is weighted by memory usage.
  • Learning rate priority is inversely weighted by accuracy improvement (i.e. increases if accuracy stagnates).
• Fixed Pruning Ratio: Pruning is constant and is stripped at the end.
• Code Quality Improvements: Added pre-commit hooks and CI linting for consistency.

[BradleyEdelman]

Merge feature/model_pruning: Introducing a refined adaptive training strategy with a constant pruning ratio that utilizes a memory/accuracy scoring system and parameter priority weighting system to identify which parameters (batch size, learning rate) to adjust, how, and when.