Epoch: 0001 train_loss= 0.69964 train_acc= 0.47576 val_loss= 0.69987 val_acc= 0.45902 time= 0.20314
Epoch: 0002 train_loss= 0.69802 train_acc= 0.52121 val_loss= 0.70006 val_acc= 0.45902 time= 0.00000
Epoch: 0003 train_loss= 0.69719 train_acc= 0.53333 val_loss= 0.70024 val_acc= 0.44262 time= 0.00000
Epoch: 0004 train_loss= 0.69644 train_acc= 0.52727 val_loss= 0.70040 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.69614 train_acc= 0.52121 val_loss= 0.70074 val_acc= 0.44262 time= 0.00000
Epoch: 0006 train_loss= 0.69524 train_acc= 0.53333 val_loss= 0.70120 val_acc= 0.44262 time= 0.00000
Epoch: 0007 train_loss= 0.69478 train_acc= 0.52727 val_loss= 0.70178 val_acc= 0.44262 time= 0.01563
Epoch: 0008 train_loss= 0.69228 train_acc= 0.53030 val_loss= 0.70245 val_acc= 0.44262 time= 0.00000
Epoch: 0009 train_loss= 0.69277 train_acc= 0.52727 val_loss= 0.70326 val_acc= 0.44262 time= 0.00000
Epoch: 0010 train_loss= 0.69213 train_acc= 0.53030 val_loss= 0.70426 val_acc= 0.44262 time= 0.01563
Epoch: 0011 train_loss= 0.69188 train_acc= 0.53030 val_loss= 0.70546 val_acc= 0.44262 time= 0.00000
Epoch: 0012 train_loss= 0.69153 train_acc= 0.52727 val_loss= 0.70652 val_acc= 0.44262 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69262 accuracy= 0.52459 time= 0.00000 
