Epoch: 0001 train_loss= 2.14065 train_acc= 0.52468 val_loss= 1.51363 val_acc= 0.45902 time= 0.78457
Epoch: 0002 train_loss= 1.42690 train_acc= 0.51948 val_loss= 1.25920 val_acc= 0.45902 time= 0.01700
Epoch: 0003 train_loss= 1.36417 train_acc= 0.51818 val_loss= 1.05231 val_acc= 0.45902 time= 0.01457
Epoch: 0004 train_loss= 1.13186 train_acc= 0.52468 val_loss= 0.87479 val_acc= 0.45902 time= 0.01617
Epoch: 0005 train_loss= 0.94075 train_acc= 0.52468 val_loss= 0.75168 val_acc= 0.45902 time= 0.01500
Epoch: 0006 train_loss= 0.76492 train_acc= 0.52727 val_loss= 0.72268 val_acc= 0.59016 time= 0.01400
Epoch: 0007 train_loss= 0.80241 train_acc= 0.50000 val_loss= 0.74043 val_acc= 0.49180 time= 0.01373
Epoch: 0008 train_loss= 0.82050 train_acc= 0.51429 val_loss= 0.76550 val_acc= 0.54098 time= 0.01207
Epoch: 0009 train_loss= 0.79144 train_acc= 0.51688 val_loss= 0.79353 val_acc= 0.55738 time= 0.01797
Epoch: 0010 train_loss= 0.85644 train_acc= 0.50519 val_loss= 0.81426 val_acc= 0.59016 time= 0.01400
Epoch: 0011 train_loss= 0.94386 train_acc= 0.51688 val_loss= 0.81873 val_acc= 0.59016 time= 0.01500
Epoch: 0012 train_loss= 0.83819 train_acc= 0.49870 val_loss= 0.80738 val_acc= 0.59016 time= 0.01400
Epoch: 0013 train_loss= 0.74669 train_acc= 0.51688 val_loss= 0.78818 val_acc= 0.59016 time= 0.01185
Epoch: 0014 train_loss= 0.74425 train_acc= 0.50519 val_loss= 0.76489 val_acc= 0.59016 time= 0.01515
Epoch: 0015 train_loss= 0.83922 train_acc= 0.50000 val_loss= 0.74076 val_acc= 0.57377 time= 0.01300
Epoch: 0016 train_loss= 0.74515 train_acc= 0.50390 val_loss= 0.72019 val_acc= 0.57377 time= 0.01416
Epoch: 0017 train_loss= 0.74917 train_acc= 0.53896 val_loss= 0.69893 val_acc= 0.59016 time= 0.01400
Epoch: 0018 train_loss= 0.76317 train_acc= 0.47922 val_loss= 0.68295 val_acc= 0.62295 time= 0.01300
Epoch: 0019 train_loss= 0.86693 train_acc= 0.52208 val_loss= 0.67165 val_acc= 0.60656 time= 0.01300
Epoch: 0020 train_loss= 0.77118 train_acc= 0.52468 val_loss= 0.66279 val_acc= 0.59016 time= 0.01300
Epoch: 0021 train_loss= 0.72984 train_acc= 0.52857 val_loss= 0.66019 val_acc= 0.65574 time= 0.01300
Epoch: 0022 train_loss= 0.75758 train_acc= 0.48961 val_loss= 0.66429 val_acc= 0.68852 time= 0.01400
Epoch: 0023 train_loss= 0.75148 train_acc= 0.54156 val_loss= 0.67413 val_acc= 0.59016 time= 0.01200
Epoch: 0024 train_loss= 0.73893 train_acc= 0.52208 val_loss= 0.68493 val_acc= 0.55738 time= 0.01312
Epoch: 0025 train_loss= 0.73984 train_acc= 0.53377 val_loss= 0.69660 val_acc= 0.50820 time= 0.01408
Early stopping...
Optimization Finished!
Test set results: cost= 0.70242 accuracy= 0.52459 time= 0.00509 
