Epoch: 0001 train_loss= 2.12613 train_acc= 0.14340 val_loss= 2.08308 val_acc= 0.13793 time= 0.66222
Epoch: 0002 train_loss= 2.14330 train_acc= 0.13208 val_loss= 2.08547 val_acc= 0.10345 time= 0.01400
Epoch: 0003 train_loss= 2.09649 train_acc= 0.14717 val_loss= 2.08831 val_acc= 0.10345 time= 0.01500
Epoch: 0004 train_loss= 2.08038 train_acc= 0.12830 val_loss= 2.08964 val_acc= 0.17241 time= 0.01400
Epoch: 0005 train_loss= 2.07986 train_acc= 0.13962 val_loss= 2.09452 val_acc= 0.10345 time= 0.01400
Epoch: 0006 train_loss= 2.06045 train_acc= 0.15472 val_loss= 2.09980 val_acc= 0.20690 time= 0.01500
Epoch: 0007 train_loss= 2.06340 train_acc= 0.19623 val_loss= 2.10269 val_acc= 0.24138 time= 0.01611
Epoch: 0008 train_loss= 2.05593 train_acc= 0.14717 val_loss= 2.10712 val_acc= 0.24138 time= 0.01400
Epoch: 0009 train_loss= 2.02975 train_acc= 0.20000 val_loss= 2.11442 val_acc= 0.24138 time= 0.01600
Epoch: 0010 train_loss= 2.04548 train_acc= 0.16981 val_loss= 2.12354 val_acc= 0.24138 time= 0.01500
Epoch: 0011 train_loss= 2.03558 train_acc= 0.20000 val_loss= 2.13362 val_acc= 0.17241 time= 0.01600
Epoch: 0012 train_loss= 2.02695 train_acc= 0.17358 val_loss= 2.14583 val_acc= 0.17241 time= 0.01400
Early stopping...
Optimization Finished!
Test set results: cost= 2.09766 accuracy= 0.11864 time= 0.00700 
