Epoch: 0001 train_loss= 1.39619 train_acc= 0.22801 val_loss= 1.40141 val_acc= 0.19643 time= 0.10938
Epoch: 0002 train_loss= 1.39786 train_acc= 0.23453 val_loss= 1.40117 val_acc= 0.28571 time= 0.01563
Epoch: 0003 train_loss= 1.39037 train_acc= 0.26059 val_loss= 1.40382 val_acc= 0.25000 time= 0.01562
Epoch: 0004 train_loss= 1.38956 train_acc= 0.28339 val_loss= 1.40712 val_acc= 0.21429 time= 0.01563
Epoch: 0005 train_loss= 1.38231 train_acc= 0.30293 val_loss= 1.41045 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38681 train_acc= 0.29967 val_loss= 1.41396 val_acc= 0.23214 time= 0.01562
Epoch: 0007 train_loss= 1.38524 train_acc= 0.26384 val_loss= 1.41825 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38263 train_acc= 0.28339 val_loss= 1.42318 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.39287 train_acc= 0.28664 val_loss= 1.42592 val_acc= 0.25000 time= 0.03125
Epoch: 0010 train_loss= 1.37946 train_acc= 0.28664 val_loss= 1.42944 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.38454 train_acc= 0.29642 val_loss= 1.43224 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37704 train_acc= 0.29316 val_loss= 1.43384 val_acc= 0.25000 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 1.39335 accuracy= 0.30973 time= 0.00000 
