Epoch: 0001 train_loss= 1.39344 train_acc= 0.26758 val_loss= 1.39156 val_acc= 0.25000 time= 0.57904
Epoch: 0002 train_loss= 1.38812 train_acc= 0.27148 val_loss= 1.39133 val_acc= 0.25000 time= 0.01563
Epoch: 0003 train_loss= 1.38488 train_acc= 0.26953 val_loss= 1.39145 val_acc= 0.25000 time= 0.00000
Epoch: 0004 train_loss= 1.38098 train_acc= 0.27539 val_loss= 1.39225 val_acc= 0.21429 time= 0.01563
Epoch: 0005 train_loss= 1.37657 train_acc= 0.28125 val_loss= 1.39353 val_acc= 0.25000 time= 0.00000
Epoch: 0006 train_loss= 1.37532 train_acc= 0.32031 val_loss= 1.39532 val_acc= 0.25000 time= 0.01562
Epoch: 0007 train_loss= 1.37318 train_acc= 0.32617 val_loss= 1.39755 val_acc= 0.25000 time= 0.00000
Epoch: 0008 train_loss= 1.37111 train_acc= 0.32422 val_loss= 1.40016 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.37154 train_acc= 0.32422 val_loss= 1.40288 val_acc= 0.25000 time= 0.00000
Epoch: 0010 train_loss= 1.37109 train_acc= 0.32422 val_loss= 1.40541 val_acc= 0.25000 time= 0.01563
Epoch: 0011 train_loss= 1.37032 train_acc= 0.32422 val_loss= 1.40761 val_acc= 0.25000 time= 0.00000
Epoch: 0012 train_loss= 1.36991 train_acc= 0.32422 val_loss= 1.40929 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39075 accuracy= 0.30088 time= 0.00000 
