Epoch: 0001 train_loss= 2.09463 train_acc= 0.08805 val_loss= 2.09093 val_acc= 0.17241 time= 0.15626
Epoch: 0002 train_loss= 2.08275 train_acc= 0.11950 val_loss= 2.08824 val_acc= 0.20690 time= 0.00000
Epoch: 0003 train_loss= 2.07268 train_acc= 0.15723 val_loss= 2.08596 val_acc= 0.13793 time= 0.01563
Epoch: 0004 train_loss= 2.06099 train_acc= 0.14465 val_loss= 2.08418 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.05961 train_acc= 0.14465 val_loss= 2.08311 val_acc= 0.17241 time= 0.01563
Epoch: 0006 train_loss= 2.04358 train_acc= 0.17610 val_loss= 2.08255 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.05758 train_acc= 0.15723 val_loss= 2.08237 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.02817 train_acc= 0.25786 val_loss= 2.08301 val_acc= 0.17241 time= 0.01563
Epoch: 0009 train_loss= 2.02540 train_acc= 0.23899 val_loss= 2.08419 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.02933 train_acc= 0.18239 val_loss= 2.08629 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.03164 train_acc= 0.16981 val_loss= 2.08904 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 1.99846 train_acc= 0.22642 val_loss= 2.09163 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09702 accuracy= 0.18644 time= 0.00000 
