logs_hyperparameter/lipophil/polyatomic/polyatomic_polyatomic_lipophil_20250806_192357.txt

--- OUTER FOLD 1/5 ---
INFO: Best params for fold 1: {'lr': 0.0006482131165247735, 'hidden_dim': 64, 'batch_size': 32}
INFO: Fold 1 Val RMSE: 0.7018, MAE: 0.5207

--- OUTER FOLD 2/5 ---
INFO: Best params for fold 2: {'lr': 0.0006175439707655367, 'hidden_dim': 128, 'batch_size': 64}
INFO: Fold 2 Val RMSE: 0.7581, MAE: 0.5697

--- OUTER FOLD 3/5 ---
INFO: Best params for fold 3: {'lr': 0.0005205409661999493, 'hidden_dim': 64, 'batch_size': 64}
INFO: Fold 3 Val RMSE: 0.7377, MAE: 0.5421

--- OUTER FOLD 4/5 ---
INFO: Best params for fold 4: {'lr': 0.0006175439707655367, 'hidden_dim': 128, 'batch_size': 64}
INFO: Fold 4 Val RMSE: 0.7037, MAE: 0.5185

--- OUTER FOLD 5/5 ---
INFO: Best params for fold 5: {'lr': 0.0008903488639350984, 'hidden_dim': 64, 'batch_size': 64}
INFO: Fold 5 Val RMSE: 0.6828, MAE: 0.5050

------ Nested Cross-Validation Summary ------
Unbiased Validation RMSE: 0.7168 ± 0.0272
Unbiased Validation MAE:  0.5312 ± 0.0226
VAL FOLD RMSEs: [0.7017787, 0.7580868, 0.7376821, 0.70374936, 0.682781]
VAL FOLD MAEs: [0.5206777, 0.56972057, 0.5421082, 0.5184605, 0.50495034]

===== STEP 2: Final Model Training & Testing =====
INFO: Finding best hyperparameters on the FULL train/val set for final model...
INFO: Optimal hyperparameters for final model: {'lr': 0.0006175439707655367, 'hidden_dim': 128, 'batch_size': 64}
INFO: Training final model...

===== STEP 3: Final Held-Out Test Evaluation =====
Test RMSE: 0.7502 (95% CI: [0.7015, 0.8015])
Test MAE:  0.5462 (95% CI: [0.5117, 0.5792])