diff --git a/model/pytorch/dcrnn_supervisor.py b/model/pytorch/dcrnn_supervisor.py
index 481c5da..8ce0224 100644
--- a/model/pytorch/dcrnn_supervisor.py
+++ b/model/pytorch/dcrnn_supervisor.py
@@ -124,11 +124,11 @@ class DCRNNSupervisor:
 
     def _train(self, base_lr,
                steps, patience=50, epochs=100, lr_decay_ratio=0.1, log_every=1, save_model=1,
-               test_every_n_epochs=10, **kwargs):
+               test_every_n_epochs=10, epsilon=1e-8, **kwargs):
         # steps is used in learning rate - will see if need to use it?
         min_val_loss = float('inf')
         wait = 0
-        optimizer = torch.optim.Adam(self.dcrnn_model.parameters(), lr=base_lr)
+        optimizer = torch.optim.Adam(self.dcrnn_model.parameters(), lr=base_lr, eps=epsilon)
 
         lr_scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=steps,
                                                             gamma=lr_decay_ratio)
@@ -159,7 +159,7 @@ class DCRNNSupervisor:
 
                 if batches_seen == 0:
                     # this is a workaround to accommodate dynamically registered parameters in DCGRUCell
-                    optimizer = torch.optim.Adam(self.dcrnn_model.parameters(), lr=base_lr)
+                    optimizer = torch.optim.Adam(self.dcrnn_model.parameters(), lr=base_lr, eps=epsilon)
 
                 loss = self._compute_loss(y, output)