|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
