Epoch: 0001 train_loss= 2.08471 train_acc= 0.11321 val_loss= 2.08053 val_acc= 0.20690 time= 0.21805
Epoch: 0002 train_loss= 2.08184 train_acc= 0.11950 val_loss= 2.08186 val_acc= 0.20690 time= 0.00600
Epoch: 0003 train_loss= 2.08025 train_acc= 0.11950 val_loss= 2.08319 val_acc= 0.20690 time= 0.00500
Epoch: 0004 train_loss= 2.07667 train_acc= 0.11950 val_loss= 2.08463 val_acc= 0.20690 time= 0.00400
Epoch: 0005 train_loss= 2.07824 train_acc= 0.12579 val_loss= 2.08614 val_acc= 0.20690 time= 0.00500
Epoch: 0006 train_loss= 2.07655 train_acc= 0.11950 val_loss= 2.08769 val_acc= 0.20690 time= 0.00500
Epoch: 0007 train_loss= 2.07687 train_acc= 0.11321 val_loss= 2.08930 val_acc= 0.20690 time= 0.00400
Epoch: 0008 train_loss= 2.07374 train_acc= 0.11321 val_loss= 2.09103 val_acc= 0.20690 time= 0.00500
Epoch: 0009 train_loss= 2.07158 train_acc= 0.13208 val_loss= 2.09285 val_acc= 0.31034 time= 0.00400
Epoch: 0010 train_loss= 2.07263 train_acc= 0.13208 val_loss= 2.09475 val_acc= 0.10345 time= 0.00500
Epoch: 0011 train_loss= 2.07019 train_acc= 0.16352 val_loss= 2.09674 val_acc= 0.06897 time= 0.00079
Epoch: 0012 train_loss= 2.06884 train_acc= 0.16981 val_loss= 2.09883 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.07123 accuracy= 0.10169 time= 0.00000 
