Epoch: 0001 train_loss= 1.39441 train_acc= 0.18893 val_loss= 1.38862 val_acc= 0.32143 time= 0.18751
Epoch: 0002 train_loss= 1.39146 train_acc= 0.24104 val_loss= 1.38573 val_acc= 0.33929 time= 0.01563
Epoch: 0003 train_loss= 1.38928 train_acc= 0.30945 val_loss= 1.38348 val_acc= 0.33929 time= 0.01563
Epoch: 0004 train_loss= 1.38698 train_acc= 0.30619 val_loss= 1.38131 val_acc= 0.33929 time= 0.01563
Epoch: 0005 train_loss= 1.38575 train_acc= 0.30619 val_loss= 1.37957 val_acc= 0.33929 time= 0.01563
Epoch: 0006 train_loss= 1.38404 train_acc= 0.30619 val_loss= 1.37801 val_acc= 0.33929 time= 0.01563
Epoch: 0007 train_loss= 1.38159 train_acc= 0.30619 val_loss= 1.37670 val_acc= 0.33929 time= 0.01563
Epoch: 0008 train_loss= 1.37997 train_acc= 0.30619 val_loss= 1.37567 val_acc= 0.33929 time= 0.01563
Epoch: 0009 train_loss= 1.37814 train_acc= 0.30619 val_loss= 1.37506 val_acc= 0.33929 time= 0.01563
Epoch: 0010 train_loss= 1.37727 train_acc= 0.30619 val_loss= 1.37487 val_acc= 0.33929 time= 0.01563
Epoch: 0011 train_loss= 1.37570 train_acc= 0.30619 val_loss= 1.37518 val_acc= 0.33929 time= 0.01563
Epoch: 0012 train_loss= 1.37455 train_acc= 0.30619 val_loss= 1.37598 val_acc= 0.33929 time= 0.00000
Epoch: 0013 train_loss= 1.37447 train_acc= 0.30619 val_loss= 1.37732 val_acc= 0.33929 time= 0.01563
Epoch: 0014 train_loss= 1.37561 train_acc= 0.30619 val_loss= 1.37915 val_acc= 0.33929 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 1.38663 accuracy= 0.31858 time= 0.01563 
