Epoch: 0001 train_loss= 0.69907 train_acc= 0.50909 val_loss= 0.70624 val_acc= 0.45902 time= 0.49972
Epoch: 0002 train_loss= 0.69671 train_acc= 0.51636 val_loss= 0.71155 val_acc= 0.45902 time= 0.00000
Epoch: 0003 train_loss= 0.69528 train_acc= 0.53273 val_loss= 0.71654 val_acc= 0.45902 time= 0.01563
Epoch: 0004 train_loss= 0.69467 train_acc= 0.52545 val_loss= 0.71855 val_acc= 0.45902 time= 0.00000
Epoch: 0005 train_loss= 0.69338 train_acc= 0.53273 val_loss= 0.71785 val_acc= 0.45902 time= 0.00000
Epoch: 0006 train_loss= 0.69534 train_acc= 0.52364 val_loss= 0.71566 val_acc= 0.45902 time= 0.01563
Epoch: 0007 train_loss= 0.69247 train_acc= 0.53273 val_loss= 0.71334 val_acc= 0.45902 time= 0.00000
Epoch: 0008 train_loss= 0.69432 train_acc= 0.52545 val_loss= 0.71093 val_acc= 0.45902 time= 0.01563
Epoch: 0009 train_loss= 0.69447 train_acc= 0.52182 val_loss= 0.70877 val_acc= 0.45902 time= 0.00000
Epoch: 0010 train_loss= 0.68998 train_acc= 0.52727 val_loss= 0.70725 val_acc= 0.45902 time= 0.00000
Epoch: 0011 train_loss= 0.69280 train_acc= 0.52364 val_loss= 0.70607 val_acc= 0.45902 time= 0.01563
Epoch: 0012 train_loss= 0.69174 train_acc= 0.51636 val_loss= 0.70559 val_acc= 0.45902 time= 0.00000
Epoch: 0013 train_loss= 0.68927 train_acc= 0.53273 val_loss= 0.70531 val_acc= 0.45902 time= 0.00000
Epoch: 0014 train_loss= 0.69120 train_acc= 0.52909 val_loss= 0.70551 val_acc= 0.45902 time= 0.01563
Epoch: 0015 train_loss= 0.68907 train_acc= 0.53091 val_loss= 0.70615 val_acc= 0.45902 time= 0.00000
Epoch: 0016 train_loss= 0.69092 train_acc= 0.52727 val_loss= 0.70679 val_acc= 0.45902 time= 0.01563
Epoch: 0017 train_loss= 0.69261 train_acc= 0.52182 val_loss= 0.70725 val_acc= 0.45902 time= 0.00000
Epoch: 0018 train_loss= 0.69005 train_acc= 0.52545 val_loss= 0.70821 val_acc= 0.45902 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68427 accuracy= 0.55738 time= 0.01563 
