Epoch: 0001 train_loss= 1.39225 train_acc= 0.25978 val_loss= 1.38890 val_acc= 0.19643 time= 0.87506
Epoch: 0002 train_loss= 1.39047 train_acc= 0.25140 val_loss= 1.38854 val_acc= 0.19643 time= 0.01563
Epoch: 0003 train_loss= 1.38933 train_acc= 0.26257 val_loss= 1.38816 val_acc= 0.19643 time= 0.00000
Epoch: 0004 train_loss= 1.38837 train_acc= 0.26257 val_loss= 1.38781 val_acc= 0.19643 time= 0.01563
Epoch: 0005 train_loss= 1.38722 train_acc= 0.26397 val_loss= 1.38753 val_acc= 0.21429 time= 0.00000
Epoch: 0006 train_loss= 1.38553 train_acc= 0.26955 val_loss= 1.38734 val_acc= 0.19643 time= 0.01563
Epoch: 0007 train_loss= 1.38634 train_acc= 0.25559 val_loss= 1.38715 val_acc= 0.14286 time= 0.00000
Epoch: 0008 train_loss= 1.38409 train_acc= 0.28631 val_loss= 1.38701 val_acc= 0.23214 time= 0.01563
Epoch: 0009 train_loss= 1.38332 train_acc= 0.28492 val_loss= 1.38691 val_acc= 0.26786 time= 0.00000
Epoch: 0010 train_loss= 1.38245 train_acc= 0.27514 val_loss= 1.38685 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.38219 train_acc= 0.29050 val_loss= 1.38687 val_acc= 0.28571 time= 0.00000
Epoch: 0012 train_loss= 1.38152 train_acc= 0.30028 val_loss= 1.38698 val_acc= 0.28571 time= 0.01563
Epoch: 0013 train_loss= 1.37842 train_acc= 0.30447 val_loss= 1.38715 val_acc= 0.28571 time= 0.00000
Epoch: 0014 train_loss= 1.37967 train_acc= 0.31704 val_loss= 1.38730 val_acc= 0.28571 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38179 accuracy= 0.30088 time= 0.00000 
