- Removed BaselineEncoder and CrossAttention classes from models.py.
- Introduced OtherInfoTokenizer for handling additional token types.
- Updated DeepHealth class to integrate OtherInfoTokenizer and manage extra pooling logic.
- Added support for extra_pool_reduce parameter to control pooling behavior.
- Modified forward methods to return structured output using DeepHealthOutput dataclass.
- Updated training scripts to accommodate changes in model architecture and output handling.
- Enhanced error handling and validation for input shapes and types.
- Implement `train_all_future.py` for training with query-conditioned all-future supervision.
- Implement `train_next_step.py` for training with next-token/next-time-point supervision.
- Introduce `train_util.py` for shared utility functions including logging, dataset splitting, and model checkpointing.
- Enhance argument parsing for both training scripts to accommodate new parameters.
- Update loss functions and model configurations to support the new training paradigms.
- Improved `parse_int_list` and `parse_float_list` functions to support JSON list input.
- Introduced `validate_dataset_metadata` function to ensure dataset metadata consistency with training configuration.
- Added multiple new files for extra information types, categorizing them into assessment-only, exposure-only, and combined types.
- Removed deprecated `merge_extra_info_types` function and adjusted related logic in `train.py`.
- Updated `save_config` function to accept additional metadata for training runs.
- Refactored model and training scripts for better clarity and maintainability.
- Implemented target construction in `targets.py` for next-token and unique-time set supervision.
- Added validation functions and utility methods for target building.
- Created a comprehensive training script in `train.py` that includes data loading, model building, optimizer setup, and training loop with early stopping and logging.
- Integrated loss functions and readout mechanisms based on target modes.
- Established dataset splitting and DataLoader configurations for training, validation, and testing.
