Epoch: 0001 train_loss= 1.72776 train_acc= 0.53333 val_loss= 1.27027 val_acc= 0.54098 time= 0.14063
Epoch: 0002 train_loss= 0.83487 train_acc= 0.54545 val_loss= 1.11068 val_acc= 0.55738 time= 0.00000
Epoch: 0003 train_loss= 1.09072 train_acc= 0.50909 val_loss= 0.96450 val_acc= 0.57377 time= 0.01563
Epoch: 0004 train_loss= 1.26718 train_acc= 0.51212 val_loss= 0.82924 val_acc= 0.62295 time= 0.01562
Epoch: 0005 train_loss= 1.71539 train_acc= 0.47879 val_loss= 0.79133 val_acc= 0.59016 time= 0.01563
Epoch: 0006 train_loss= 1.12387 train_acc= 0.49091 val_loss= 0.77215 val_acc= 0.59016 time= 0.01562
Epoch: 0007 train_loss= 0.93725 train_acc= 0.51515 val_loss= 0.75319 val_acc= 0.59016 time= 0.01563
Epoch: 0008 train_loss= 0.89636 train_acc= 0.50909 val_loss= 0.72785 val_acc= 0.60656 time= 0.01563
Epoch: 0009 train_loss= 1.03754 train_acc= 0.47879 val_loss= 0.70585 val_acc= 0.62295 time= 0.00000
Epoch: 0010 train_loss= 1.05247 train_acc= 0.47576 val_loss= 0.69752 val_acc= 0.62295 time= 0.01563
Epoch: 0011 train_loss= 0.85700 train_acc= 0.48788 val_loss= 0.69367 val_acc= 0.60656 time= 0.01563
Epoch: 0012 train_loss= 0.82557 train_acc= 0.49394 val_loss= 0.69809 val_acc= 0.62295 time= 0.01563
Epoch: 0013 train_loss= 1.27068 train_acc= 0.44545 val_loss= 0.71088 val_acc= 0.63934 time= 0.00000
Epoch: 0014 train_loss= 0.85020 train_acc= 0.53939 val_loss= 0.71801 val_acc= 0.63934 time= 0.02205
Epoch: 0015 train_loss= 0.94252 train_acc= 0.44242 val_loss= 0.72150 val_acc= 0.63934 time= 0.01100
Epoch: 0016 train_loss= 0.88997 train_acc= 0.54848 val_loss= 0.71719 val_acc= 0.63934 time= 0.01100
Epoch: 0017 train_loss= 0.96596 train_acc= 0.47576 val_loss= 0.72498 val_acc= 0.62295 time= 0.01100
Early stopping...
Optimization Finished!
Test set results: cost= 0.75781 accuracy= 0.44262 time= 0.00400 
