Epoch: 0001 train_loss= 0.75856 train_acc= 0.53636 val_loss= 0.77836 val_acc= 0.51613 time= 0.35994
Epoch: 0002 train_loss= 0.71384 train_acc= 0.55152 val_loss= 0.83894 val_acc= 0.48387 time= 0.03125
Epoch: 0003 train_loss= 0.70962 train_acc= 0.55152 val_loss= 0.88717 val_acc= 0.45161 time= 0.01563
Epoch: 0004 train_loss= 0.71605 train_acc= 0.55152 val_loss= 0.81991 val_acc= 0.53226 time= 0.03125
Epoch: 0005 train_loss= 0.77673 train_acc= 0.60000 val_loss= 0.71985 val_acc= 0.50000 time= 0.01563
Epoch: 0006 train_loss= 0.68459 train_acc= 0.52727 val_loss= 0.71322 val_acc= 0.45161 time= 0.01562
Epoch: 0007 train_loss= 0.68887 train_acc= 0.56061 val_loss= 0.72518 val_acc= 0.46774 time= 0.03617
Epoch: 0008 train_loss= 0.70160 train_acc= 0.54545 val_loss= 0.73000 val_acc= 0.45161 time= 0.01100
Epoch: 0009 train_loss= 0.75324 train_acc= 0.50909 val_loss= 0.73094 val_acc= 0.45161 time= 0.03126
Epoch: 0010 train_loss= 0.72331 train_acc= 0.54545 val_loss= 0.72589 val_acc= 0.45161 time= 0.01563
Epoch: 0011 train_loss= 0.70541 train_acc= 0.54242 val_loss= 0.72309 val_acc= 0.45161 time= 0.03125
Epoch: 0012 train_loss= 0.70625 train_acc= 0.53636 val_loss= 0.71371 val_acc= 0.45161 time= 0.01563
Epoch: 0013 train_loss= 0.69999 train_acc= 0.52424 val_loss= 0.70785 val_acc= 0.45161 time= 0.03125
Epoch: 0014 train_loss= 0.68524 train_acc= 0.54545 val_loss= 0.70571 val_acc= 0.46774 time= 0.01563
Epoch: 0015 train_loss= 0.70550 train_acc= 0.53939 val_loss= 0.70597 val_acc= 0.48387 time= 0.01563
Epoch: 0016 train_loss= 0.69532 train_acc= 0.53636 val_loss= 0.70803 val_acc= 0.48387 time= 0.03125
Epoch: 0017 train_loss= 0.69359 train_acc= 0.58788 val_loss= 0.70825 val_acc= 0.48387 time= 0.01563
Epoch: 0018 train_loss= 0.70516 train_acc= 0.51212 val_loss= 0.70953 val_acc= 0.53226 time= 0.01563
Epoch: 0019 train_loss= 0.73426 train_acc= 0.54848 val_loss= 0.71483 val_acc= 0.54839 time= 0.03125
Early stopping...
Optimization Finished!
Test set results: cost= 0.79640 accuracy= 0.50806 time= 0.00000 
