8723bf7600
Enhance Trainer class: add delta_scale logging for improved training statistics
2026-01-09 13:28:11 +08:00
dc34d51864
Add rank parameter to TrainConfig and update argument parsing for low-rank parameterization
2026-01-09 13:18:09 +08:00
1fa6d55d79
Refactor PiecewiseExponentialLoss and WeibullNLLLoss: remove lightweight numerical protections and improve error handling for input validation
2026-01-09 13:06:43 +08:00
b54c54a60b
Refactor Trainer class: improve training statistics calculation and logging for NLL and regularization
2026-01-09 12:49:29 +08:00
aff0fe480b
Refactor model and training scripts: remove unused imports and add FactorizedHead class for improved modularity
2026-01-09 12:01:52 +08:00
c70c3cd71e
Reorganize import statements for consistency and clarity in model and training scripts
2026-01-09 10:16:03 +08:00
d7600514af
Update Trainer class to rename parameters for clarity in embedding configuration
2026-01-08 17:11:19 +08:00
d20d32ba22
Add multi-GPU experiment runner script and experiments configuration
2026-01-08 13:57:34 +08:00
01a96d37ea
Enhance DataLoader configuration and improve tensor transfer efficiency in Trainer class
2026-01-08 13:20:32 +08:00
5382f9f159
Remove EMA model implementation from Trainer class and related parameters from TrainConfig
2026-01-08 13:14:29 +08:00
615e2fe748
Refactor PiecewiseExponentialLoss for clarity and numerical stability improvements
2026-01-08 13:05:53 +08:00
06a01d2893
Add PiecewiseExponentialLoss class and update TrainConfig for new loss type
2026-01-08 12:45:31 +08:00
7c36f7a007
Update age_encoder parameter choices in TrainConfig and argument parser for clarity
2026-01-08 11:38:45 +08:00
9eda00ea48
Add n_tech_tokens parameter to DelphiFork and SapDelphi model initializations
2026-01-08 11:36:23 +08:00
1d1f568a3f
Rename age_encoder parameter to age_encoder_type for clarity in Trainer class
2026-01-08 11:34:44 +08:00
8293f7ee24
Enhance TabularEncoder with BatchNorm and AutoDiscretization for continuous features
2026-01-08 00:24:43 +08:00
33ba7e6c1d
Refactor training logic to improve early stopping mechanism and variable naming
2026-01-08 00:07:15 +08:00
811b2e1a46
Implement training script for Delphi model with configurable parameters
2026-01-07 23:57:29 +08:00
6984b254b3
Add loss functions and model architecture for time-to-event prediction
...
- Implemented ExponentialNLLLoss and WeibullNLLLoss in losses.py for negative log-likelihood calculations.
- Developed TabularEncoder class in model.py for encoding tabular features.
- Created DelphiFork and SapDelphi classes in model.py for time-to-event prediction using transformer architecture.
- Added data preparation scripts in prepare_data.R and prepare_data.py for processing UK Biobank data, including handling field mappings and event data extraction.
2026-01-07 21:32:00 +08:00
5d1d79b908
Initial commit
2026-01-07 21:27:38 +08:00
