Epoch: 0001 train_loss= 0.95286 train_acc= 0.46753 val_loss= 0.91458 val_acc= 0.36066 time= 0.96881
Epoch: 0002 train_loss= 0.95885 train_acc= 0.52338 val_loss= 0.73310 val_acc= 0.39344 time= 0.01563
Epoch: 0003 train_loss= 0.88439 train_acc= 0.48312 val_loss= 0.69879 val_acc= 0.54098 time= 0.03125
Epoch: 0004 train_loss= 0.77638 train_acc= 0.50260 val_loss= 0.69545 val_acc= 0.55738 time= 0.01563
Epoch: 0005 train_loss= 0.80697 train_acc= 0.53506 val_loss= 0.68972 val_acc= 0.57377 time= 0.03125
Epoch: 0006 train_loss= 0.76798 train_acc= 0.50779 val_loss= 0.70202 val_acc= 0.52459 time= 0.01562
Epoch: 0007 train_loss= 0.72304 train_acc= 0.50909 val_loss= 0.73515 val_acc= 0.36066 time= 0.03125
Epoch: 0008 train_loss= 0.71599 train_acc= 0.50519 val_loss= 0.75710 val_acc= 0.34426 time= 0.01563
Epoch: 0009 train_loss= 0.73820 train_acc= 0.50390 val_loss= 0.77759 val_acc= 0.36066 time= 0.03125
Epoch: 0010 train_loss= 0.73473 train_acc= 0.50519 val_loss= 0.77807 val_acc= 0.34426 time= 0.01563
Epoch: 0011 train_loss= 0.75650 train_acc= 0.50779 val_loss= 0.76214 val_acc= 0.34426 time= 0.03125
Epoch: 0012 train_loss= 0.74441 train_acc= 0.51039 val_loss= 0.75419 val_acc= 0.40984 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.70245 accuracy= 0.58197 time= 0.01563 
