Epoch: 0001 train_loss= 1.39629 train_acc= 0.24219 val_loss= 1.39950 val_acc= 0.26786 time= 0.18751
Epoch: 0002 train_loss= 1.39428 train_acc= 0.29492 val_loss= 1.39873 val_acc= 0.19643 time= 0.01563
Epoch: 0003 train_loss= 1.39287 train_acc= 0.30078 val_loss= 1.39790 val_acc= 0.26786 time= 0.01563
Epoch: 0004 train_loss= 1.39450 train_acc= 0.27734 val_loss= 1.39872 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38622 train_acc= 0.30273 val_loss= 1.40111 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.37779 train_acc= 0.29688 val_loss= 1.40434 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.37819 train_acc= 0.31250 val_loss= 1.40742 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.37487 train_acc= 0.32617 val_loss= 1.41030 val_acc= 0.25000 time= 0.01563
Epoch: 0009 train_loss= 1.37544 train_acc= 0.32812 val_loss= 1.41374 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.37881 train_acc= 0.30078 val_loss= 1.41733 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.37973 train_acc= 0.30859 val_loss= 1.41979 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.37141 train_acc= 0.32422 val_loss= 1.42193 val_acc= 0.28571 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.39781 accuracy= 0.24779 time= 0.01563 
