Table 2.

Hyperparameters of best RNN, LSTM and GRU models along with their AUPRC score on validation and test

Model Type	Hidden Size	LSTM Layers	Bi LSTM	Hidden Layers	Dropout Probability	Batch Size	Epochs	Learning Rate	AUPRC on Validation Set	AUPRC on Test Set
RNN	256	2	TRUE	0	0.4	256	60	0.00100	0.7643	0.5711
LSTM	512	1	TRUE	2	0.4	64	50	0.00010	0.7403	0.7208
GRU	128	2	TRUE	0	0.1	64	30	0.00050	0.7427	0.6859