Epoch: 0001 train_loss= 1.24690 train_acc= 0.48727 val_loss= 1.53523 val_acc= 0.47541 time= 0.64067
Epoch: 0002 train_loss= 1.26620 train_acc= 0.55091 val_loss= 1.72931 val_acc= 0.45902 time= 0.03125
Epoch: 0003 train_loss= 1.34224 train_acc= 0.55455 val_loss= 1.20988 val_acc= 0.47541 time= 0.03514
Epoch: 0004 train_loss= 2.50689 train_acc= 0.47273 val_loss= 1.76430 val_acc= 0.45902 time= 0.02100
Epoch: 0005 train_loss= 3.48626 train_acc= 0.55455 val_loss= 1.92659 val_acc= 0.45902 time= 0.02300
Epoch: 0006 train_loss= 2.52449 train_acc= 0.54000 val_loss= 1.59352 val_acc= 0.45902 time= 0.02301
Epoch: 0007 train_loss= 0.92225 train_acc= 0.55273 val_loss= 1.00688 val_acc= 0.45902 time= 0.02300
Epoch: 0008 train_loss= 1.10313 train_acc= 0.51091 val_loss= 0.94942 val_acc= 0.47541 time= 0.02501
Epoch: 0009 train_loss= 0.93489 train_acc= 0.49091 val_loss= 1.00804 val_acc= 0.45902 time= 0.02201
Epoch: 0010 train_loss= 1.93412 train_acc= 0.48909 val_loss= 1.23845 val_acc= 0.45902 time= 0.02401
Epoch: 0011 train_loss= 1.12746 train_acc= 0.45818 val_loss= 1.55377 val_acc= 0.45902 time= 0.02300
Epoch: 0012 train_loss= 0.92881 train_acc= 0.52545 val_loss= 1.77531 val_acc= 0.45902 time= 0.02401
Early stopping...
Optimization Finished!
Test set results: cost= 0.69436 accuracy= 0.58197 time= 0.01000 
