Epoch: 0001 train_loss= 2.08176 train_acc= 0.10692 val_loss= 2.07653 val_acc= 0.13793 time= 0.25347
Epoch: 0002 train_loss= 2.07853 train_acc= 0.10063 val_loss= 2.07611 val_acc= 0.13793 time= 0.00000
Epoch: 0003 train_loss= 2.07708 train_acc= 0.11950 val_loss= 2.07580 val_acc= 0.13793 time= 0.00000
Epoch: 0004 train_loss= 2.07389 train_acc= 0.13208 val_loss= 2.07556 val_acc= 0.13793 time= 0.01563
Epoch: 0005 train_loss= 2.07378 train_acc= 0.12579 val_loss= 2.07542 val_acc= 0.17241 time= 0.00000
Epoch: 0006 train_loss= 2.07205 train_acc= 0.13208 val_loss= 2.07535 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.06777 train_acc= 0.20126 val_loss= 2.07544 val_acc= 0.17241 time= 0.01562
Epoch: 0008 train_loss= 2.06761 train_acc= 0.18868 val_loss= 2.07562 val_acc= 0.17241 time= 0.00000
Epoch: 0009 train_loss= 2.06519 train_acc= 0.19497 val_loss= 2.07590 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.06354 train_acc= 0.19497 val_loss= 2.07629 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.06010 train_acc= 0.18868 val_loss= 2.07684 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.05982 train_acc= 0.18868 val_loss= 2.07758 val_acc= 0.17241 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.05500 accuracy= 0.11864 time= 0.00000 
