Epoch: 0001 train_loss= 0.69574 train_acc= 0.50649 val_loss= 0.70140 val_acc= 0.44262 time= 0.89354
Epoch: 0002 train_loss= 0.69471 train_acc= 0.48701 val_loss= 0.70226 val_acc= 0.44262 time= 0.01563
Epoch: 0003 train_loss= 0.69311 train_acc= 0.53117 val_loss= 0.70149 val_acc= 0.42623 time= 0.00000
Epoch: 0004 train_loss= 0.69597 train_acc= 0.49481 val_loss= 0.70022 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.69591 train_acc= 0.47143 val_loss= 0.69913 val_acc= 0.50820 time= 0.00000
Epoch: 0006 train_loss= 0.69767 train_acc= 0.49221 val_loss= 0.69871 val_acc= 0.52459 time= 0.00000
Epoch: 0007 train_loss= 0.69639 train_acc= 0.48831 val_loss= 0.69860 val_acc= 0.50820 time= 0.01563
Epoch: 0008 train_loss= 0.69569 train_acc= 0.47922 val_loss= 0.69867 val_acc= 0.47541 time= 0.00000
Epoch: 0009 train_loss= 0.69488 train_acc= 0.51429 val_loss= 0.69888 val_acc= 0.39344 time= 0.00000
Epoch: 0010 train_loss= 0.69628 train_acc= 0.51818 val_loss= 0.69917 val_acc= 0.42623 time= 0.01563
Epoch: 0011 train_loss= 0.69597 train_acc= 0.47922 val_loss= 0.69954 val_acc= 0.44262 time= 0.00000
Epoch: 0012 train_loss= 0.69553 train_acc= 0.48312 val_loss= 0.69955 val_acc= 0.44262 time= 0.01563
Epoch: 0013 train_loss= 0.69365 train_acc= 0.50260 val_loss= 0.69953 val_acc= 0.44262 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68956 accuracy= 0.54918 time= 0.00000 
