Epoch: 0001 train_loss= 2.08319 train_acc= 0.15723 val_loss= 2.09679 val_acc= 0.17241 time= 0.15626
Epoch: 0002 train_loss= 2.10593 train_acc= 0.09434 val_loss= 2.09120 val_acc= 0.17241 time= 0.00000
Epoch: 0003 train_loss= 2.08358 train_acc= 0.15723 val_loss= 2.08686 val_acc= 0.17241 time= 0.01562
Epoch: 0004 train_loss= 2.07366 train_acc= 0.16352 val_loss= 2.08407 val_acc= 0.13793 time= 0.00000
Epoch: 0005 train_loss= 2.06591 train_acc= 0.16352 val_loss= 2.08248 val_acc= 0.03448 time= 0.01563
Epoch: 0006 train_loss= 2.05937 train_acc= 0.19497 val_loss= 2.08142 val_acc= 0.06897 time= 0.01563
Epoch: 0007 train_loss= 2.06358 train_acc= 0.16352 val_loss= 2.08124 val_acc= 0.13793 time= 0.00000
Epoch: 0008 train_loss= 2.04714 train_acc= 0.20755 val_loss= 2.08224 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.05717 train_acc= 0.19497 val_loss= 2.08366 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.04443 train_acc= 0.18239 val_loss= 2.08526 val_acc= 0.06897 time= 0.01562
Epoch: 0011 train_loss= 2.04205 train_acc= 0.23270 val_loss= 2.08706 val_acc= 0.06897 time= 0.00000
Epoch: 0012 train_loss= 2.03556 train_acc= 0.22013 val_loss= 2.08906 val_acc= 0.03448 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.07175 accuracy= 0.20339 time= 0.00000 
