Epoch: 0001 train_loss= 1.38976 train_acc= 0.24581 val_loss= 1.39038 val_acc= 0.21429 time= 0.90679
Epoch: 0002 train_loss= 1.38780 train_acc= 0.24721 val_loss= 1.38960 val_acc= 0.21429 time= 0.01563
Epoch: 0003 train_loss= 1.38600 train_acc= 0.25140 val_loss= 1.38892 val_acc= 0.21429 time= 0.00000
Epoch: 0004 train_loss= 1.38511 train_acc= 0.23883 val_loss= 1.38828 val_acc= 0.19643 time= 0.00000
Epoch: 0005 train_loss= 1.38443 train_acc= 0.26117 val_loss= 1.38772 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38293 train_acc= 0.28212 val_loss= 1.38722 val_acc= 0.25000 time= 0.00000
Epoch: 0007 train_loss= 1.38275 train_acc= 0.30447 val_loss= 1.38678 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38086 train_acc= 0.32402 val_loss= 1.38644 val_acc= 0.25000 time= 0.00000
Epoch: 0009 train_loss= 1.37860 train_acc= 0.32263 val_loss= 1.38620 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.37926 train_acc= 0.32123 val_loss= 1.38606 val_acc= 0.25000 time= 0.00000
Epoch: 0011 train_loss= 1.37809 train_acc= 0.32123 val_loss= 1.38597 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37781 train_acc= 0.32123 val_loss= 1.38598 val_acc= 0.25000 time= 0.00000
Epoch: 0013 train_loss= 1.37715 train_acc= 0.32123 val_loss= 1.38610 val_acc= 0.25000 time= 0.01563
Epoch: 0014 train_loss= 1.37564 train_acc= 0.32123 val_loss= 1.38630 val_acc= 0.25000 time= 0.00000
Epoch: 0015 train_loss= 1.37562 train_acc= 0.32123 val_loss= 1.38659 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38632 accuracy= 0.28319 time= 0.00000 
