Epoch: 0001 train_loss= 2.08820 train_acc= 0.14717 val_loss= 2.07832 val_acc= 0.17241 time= 0.17188
Epoch: 0002 train_loss= 2.08730 train_acc= 0.15094 val_loss= 2.07670 val_acc= 0.10345 time= 0.01563
Epoch: 0003 train_loss= 2.07981 train_acc= 0.19623 val_loss= 2.07480 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.07800 train_acc= 0.15849 val_loss= 2.07240 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.07960 train_acc= 0.14340 val_loss= 2.06951 val_acc= 0.10345 time= 0.01563
Epoch: 0006 train_loss= 2.07239 train_acc= 0.19623 val_loss= 2.06656 val_acc= 0.10345 time= 0.01562
Epoch: 0007 train_loss= 2.07110 train_acc= 0.17358 val_loss= 2.06418 val_acc= 0.10345 time= 0.00000
Epoch: 0008 train_loss= 2.06223 train_acc= 0.18868 val_loss= 2.06227 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.06329 train_acc= 0.18491 val_loss= 2.06124 val_acc= 0.13793 time= 0.00000
Epoch: 0010 train_loss= 2.06538 train_acc= 0.16981 val_loss= 2.05990 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.05757 train_acc= 0.19245 val_loss= 2.05878 val_acc= 0.13793 time= 0.01563
Epoch: 0012 train_loss= 2.05875 train_acc= 0.18113 val_loss= 2.05769 val_acc= 0.13793 time= 0.00000
Epoch: 0013 train_loss= 2.05943 train_acc= 0.18491 val_loss= 2.05816 val_acc= 0.17241 time= 0.01562
Epoch: 0014 train_loss= 2.05894 train_acc= 0.18113 val_loss= 2.05960 val_acc= 0.17241 time= 0.00000
Epoch: 0015 train_loss= 2.05387 train_acc= 0.16604 val_loss= 2.06218 val_acc= 0.17241 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.04174 accuracy= 0.11864 time= 0.00000 
