Table 2 Hyperparameters for QSPR/QSAR Model Fine-tuning
From: Inductive transfer learning for molecular activity prediction: Next-Gen QSAR Models with MolPMoFiT
Layer groups | Base Learning Rate | Epochs |
|---|---|---|
Linear head only | 3e−2 | 4 |
Linear head + final LSTM layer | 5e−3 | 4 |
Linear head + final two LSTM layers | 5e−4 | 4 |
Full model | 5e−5 | 6 |