Epoch: 0001 train_loss= 1.39377 train_acc= 0.24441 val_loss= 1.39133 val_acc= 0.25000 time= 0.67433
Epoch: 0002 train_loss= 1.39158 train_acc= 0.24441 val_loss= 1.39124 val_acc= 0.25000 time= 0.01700
Epoch: 0003 train_loss= 1.39053 train_acc= 0.24441 val_loss= 1.39114 val_acc= 0.25000 time= 0.01600
Epoch: 0004 train_loss= 1.38973 train_acc= 0.24441 val_loss= 1.39107 val_acc= 0.25000 time= 0.01700
Epoch: 0005 train_loss= 1.38892 train_acc= 0.24581 val_loss= 1.39105 val_acc= 0.25000 time= 0.01700
Epoch: 0006 train_loss= 1.38762 train_acc= 0.24721 val_loss= 1.39110 val_acc= 0.25000 time= 0.01700
Epoch: 0007 train_loss= 1.38668 train_acc= 0.26536 val_loss= 1.39125 val_acc= 0.21429 time= 0.01500
Epoch: 0008 train_loss= 1.38594 train_acc= 0.32123 val_loss= 1.39150 val_acc= 0.21429 time= 0.01500
Epoch: 0009 train_loss= 1.38502 train_acc= 0.31145 val_loss= 1.39187 val_acc= 0.21429 time= 0.01600
Epoch: 0010 train_loss= 1.38359 train_acc= 0.32402 val_loss= 1.39240 val_acc= 0.21429 time= 0.01600
Epoch: 0011 train_loss= 1.38255 train_acc= 0.32263 val_loss= 1.39308 val_acc= 0.21429 time= 0.01600
Epoch: 0012 train_loss= 1.38155 train_acc= 0.32263 val_loss= 1.39395 val_acc= 0.21429 time= 0.01500
Early stopping...
Optimization Finished!
Test set results: cost= 1.37968 accuracy= 0.30973 time= 0.00700 
