Epoch: 0001 train_loss= 2.08662 train_acc= 0.10692 val_loss= 2.08177 val_acc= 0.10345 time= 0.26564
Epoch: 0002 train_loss= 2.08567 train_acc= 0.11321 val_loss= 2.08196 val_acc= 0.10345 time= 0.00000
Epoch: 0003 train_loss= 2.08417 train_acc= 0.11321 val_loss= 2.08237 val_acc= 0.10345 time= 0.01563
Epoch: 0004 train_loss= 2.08282 train_acc= 0.10692 val_loss= 2.08284 val_acc= 0.10345 time= 0.00000
Epoch: 0005 train_loss= 2.08044 train_acc= 0.13208 val_loss= 2.08340 val_acc= 0.17241 time= 0.00000
Epoch: 0006 train_loss= 2.07983 train_acc= 0.15094 val_loss= 2.08421 val_acc= 0.17241 time= 0.01563
Epoch: 0007 train_loss= 2.07762 train_acc= 0.16352 val_loss= 2.08517 val_acc= 0.17241 time= 0.00000
Epoch: 0008 train_loss= 2.07729 train_acc= 0.16352 val_loss= 2.08631 val_acc= 0.17241 time= 0.00000
Epoch: 0009 train_loss= 2.07496 train_acc= 0.16352 val_loss= 2.08753 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.07318 train_acc= 0.16352 val_loss= 2.08887 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.07392 train_acc= 0.15723 val_loss= 2.09045 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.07103 train_acc= 0.16352 val_loss= 2.09228 val_acc= 0.17241 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08633 accuracy= 0.13559 time= 0.01563 
