Epoch: 0001 train_loss= 2.08584 train_acc= 0.13585 val_loss= 2.07833 val_acc= 0.20690 time= 0.20314
Epoch: 0002 train_loss= 2.08353 train_acc= 0.13208 val_loss= 2.07519 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.08136 train_acc= 0.13585 val_loss= 2.07227 val_acc= 0.17241 time= 0.01563
Epoch: 0004 train_loss= 2.07944 train_acc= 0.15849 val_loss= 2.06937 val_acc= 0.17241 time= 0.00000
Epoch: 0005 train_loss= 2.07856 train_acc= 0.16981 val_loss= 2.06653 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.07685 train_acc= 0.17358 val_loss= 2.06376 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.07586 train_acc= 0.16981 val_loss= 2.06110 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.07516 train_acc= 0.14717 val_loss= 2.05867 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.07341 train_acc= 0.16604 val_loss= 2.05644 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.07177 train_acc= 0.16981 val_loss= 2.05443 val_acc= 0.17241 time= 0.01562
Epoch: 0011 train_loss= 2.07191 train_acc= 0.16981 val_loss= 2.05282 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.07011 train_acc= 0.16604 val_loss= 2.05148 val_acc= 0.17241 time= 0.01563
Epoch: 0013 train_loss= 2.06941 train_acc= 0.16604 val_loss= 2.05057 val_acc= 0.17241 time= 0.00000
Epoch: 0014 train_loss= 2.06770 train_acc= 0.16604 val_loss= 2.04998 val_acc= 0.17241 time= 0.01563
Epoch: 0015 train_loss= 2.06655 train_acc= 0.16604 val_loss= 2.04972 val_acc= 0.17241 time= 0.01563
Epoch: 0016 train_loss= 2.06615 train_acc= 0.16604 val_loss= 2.04983 val_acc= 0.17241 time= 0.00000
Epoch: 0017 train_loss= 2.06515 train_acc= 0.16604 val_loss= 2.05024 val_acc= 0.17241 time= 0.01563
Epoch: 0018 train_loss= 2.06402 train_acc= 0.16604 val_loss= 2.05089 val_acc= 0.17241 time= 0.00000
Epoch: 0019 train_loss= 2.06339 train_acc= 0.16604 val_loss= 2.05171 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.04906 accuracy= 0.23729 time= 0.00000 
