README.md

metadata

license: mit

ESM-2 QLoRA for Binding Site Prediction

In this model, we wanted to see how the performance metrics were effected by adapting additional weight matrices with QLoRA. This was shown to be the most important hyperparameter for improvement in performance metrics by far, whereas hyperparameters such as rank and scaling factor were shown to be negligible in importance, with lower rank being just as good as higher rank. So, we decided to test the difference between simply using the query, key, and value weight matrix adapters to using adapters for all possible weight matrices. The comparison for the first epoch can be seen below. Note the minor performance improvements for the model using every possible weight matrix.

This model

Test (epoch 1): 
'eval_loss': 0.41490185260772705,
'eval_accuracy': 0.8625347674451358,
'eval_precision': 0.11370668247419904,
'eval_recall': 0.7800926533683039,
'eval_f1': 0.19848246486644372,
'eval_auc': 0.8222331548742136,
'eval_mcc': 0.2639007297474409}

Query, Key, Value only Model:

Test (epoch 1):
{'eval_loss': 0.3398605287075043,
'eval_accuracy': 0.8557050926566265,
'eval_precision': 0.10792930844408741,
'eval_recall': 0.7726298654561553,
'eval_f1': 0.18940102955847055,
'eval_auc': 0.8150939843855006,
'eval_mcc': 0.2535956911257298}