Epoch: 0001 train_loss= 2.10211 train_acc= 0.13962 val_loss= 2.05663 val_acc= 0.13793 time= 0.65660
Epoch: 0002 train_loss= 2.12479 train_acc= 0.15472 val_loss= 2.05999 val_acc= 0.24138 time= 0.01600
Epoch: 0003 train_loss= 2.09289 train_acc= 0.15849 val_loss= 2.06962 val_acc= 0.24138 time= 0.01600
Epoch: 0004 train_loss= 2.07608 train_acc= 0.12075 val_loss= 2.08136 val_acc= 0.10345 time= 0.01400
Epoch: 0005 train_loss= 2.07006 train_acc= 0.15472 val_loss= 2.09440 val_acc= 0.10345 time= 0.01600
Epoch: 0006 train_loss= 2.05242 train_acc= 0.16604 val_loss= 2.10810 val_acc= 0.10345 time= 0.01600
Epoch: 0007 train_loss= 2.06012 train_acc= 0.15849 val_loss= 2.12043 val_acc= 0.10345 time= 0.01700
Epoch: 0008 train_loss= 2.04611 train_acc= 0.13962 val_loss= 2.13028 val_acc= 0.10345 time= 0.01703
Epoch: 0009 train_loss= 2.05671 train_acc= 0.13962 val_loss= 2.14102 val_acc= 0.17241 time= 0.02098
Epoch: 0010 train_loss= 2.05005 train_acc= 0.17736 val_loss= 2.15032 val_acc= 0.20690 time= 0.01700
Epoch: 0011 train_loss= 2.05227 train_acc= 0.15094 val_loss= 2.15982 val_acc= 0.20690 time= 0.01900
Epoch: 0012 train_loss= 2.05378 train_acc= 0.13585 val_loss= 2.17023 val_acc= 0.20690 time= 0.01800
Early stopping...
Optimization Finished!
Test set results: cost= 2.10924 accuracy= 0.10169 time= 0.01000 
