Epoch: 0001 train_loss= 0.69874 train_acc= 0.50130 val_loss= 0.69990 val_acc= 0.44262 time= 0.78631
Epoch: 0002 train_loss= 0.69883 train_acc= 0.49740 val_loss= 0.69824 val_acc= 0.45902 time= 0.00000
Epoch: 0003 train_loss= 0.69750 train_acc= 0.50649 val_loss= 0.69727 val_acc= 0.42623 time= 0.01562
Epoch: 0004 train_loss= 0.69748 train_acc= 0.51558 val_loss= 0.69683 val_acc= 0.39344 time= 0.00000
Epoch: 0005 train_loss= 0.69828 train_acc= 0.47143 val_loss= 0.69670 val_acc= 0.37705 time= 0.00000
Epoch: 0006 train_loss= 0.69661 train_acc= 0.50519 val_loss= 0.69677 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.69586 train_acc= 0.51169 val_loss= 0.69698 val_acc= 0.45902 time= 0.00000
Epoch: 0008 train_loss= 0.69539 train_acc= 0.49740 val_loss= 0.69727 val_acc= 0.45902 time= 0.01563
Epoch: 0009 train_loss= 0.69529 train_acc= 0.49870 val_loss= 0.69752 val_acc= 0.44262 time= 0.00000
Epoch: 0010 train_loss= 0.69511 train_acc= 0.48961 val_loss= 0.69775 val_acc= 0.42623 time= 0.00000
Epoch: 0011 train_loss= 0.69566 train_acc= 0.49481 val_loss= 0.69797 val_acc= 0.42623 time= 0.01563
Epoch: 0012 train_loss= 0.69512 train_acc= 0.50390 val_loss= 0.69798 val_acc= 0.40984 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69557 accuracy= 0.48361 time= 0.00000 
