Epoch: 0001 train_loss= 2.08711 train_acc= 0.13208 val_loss= 2.08715 val_acc= 0.17241 time= 0.18751
Epoch: 0002 train_loss= 2.08471 train_acc= 0.15723 val_loss= 2.08764 val_acc= 0.13793 time= 0.01563
Epoch: 0003 train_loss= 2.08250 train_acc= 0.13836 val_loss= 2.08865 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.08046 train_acc= 0.13208 val_loss= 2.09040 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07867 train_acc= 0.12579 val_loss= 2.09281 val_acc= 0.13793 time= 0.00000
Epoch: 0006 train_loss= 2.07625 train_acc= 0.17610 val_loss= 2.09572 val_acc= 0.00000 time= 0.01563
Epoch: 0007 train_loss= 2.07430 train_acc= 0.15094 val_loss= 2.09902 val_acc= 0.00000 time= 0.00000
Epoch: 0008 train_loss= 2.07316 train_acc= 0.13208 val_loss= 2.10239 val_acc= 0.00000 time= 0.01563
Epoch: 0009 train_loss= 2.07221 train_acc= 0.10692 val_loss= 2.10586 val_acc= 0.00000 time= 0.00000
Epoch: 0010 train_loss= 2.06968 train_acc= 0.15723 val_loss= 2.10946 val_acc= 0.13793 time= 0.01563
Epoch: 0011 train_loss= 2.07014 train_acc= 0.13836 val_loss= 2.11300 val_acc= 0.13793 time= 0.00000
Epoch: 0012 train_loss= 2.06710 train_acc= 0.15723 val_loss= 2.11635 val_acc= 0.13793 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07106 accuracy= 0.22034 time= 0.00000 
