Epoch: 0001 train_loss= 1.05431 train_acc= 0.48571 val_loss= 0.73501 val_acc= 0.56452 time= 0.29733
Epoch: 0002 train_loss= 0.95556 train_acc= 0.49091 val_loss= 0.73837 val_acc= 0.54839 time= 0.01519
Epoch: 0003 train_loss= 1.67013 train_acc= 0.48571 val_loss= 0.73290 val_acc= 0.53226 time= 0.01563
Epoch: 0004 train_loss= 1.36296 train_acc= 0.49221 val_loss= 0.76270 val_acc= 0.50000 time= 0.01563
Epoch: 0005 train_loss= 1.16156 train_acc= 0.48052 val_loss= 0.79575 val_acc= 0.54839 time= 0.00000
Epoch: 0006 train_loss= 0.96319 train_acc= 0.52338 val_loss= 0.83612 val_acc= 0.58065 time= 0.01563
Epoch: 0007 train_loss= 1.02060 train_acc= 0.48961 val_loss= 0.85407 val_acc= 0.54839 time= 0.01563
Epoch: 0008 train_loss= 1.24474 train_acc= 0.50000 val_loss= 0.83251 val_acc= 0.53226 time= 0.01563
Epoch: 0009 train_loss= 1.26911 train_acc= 0.51039 val_loss= 0.79669 val_acc= 0.53226 time= 0.01563
Epoch: 0010 train_loss= 1.06037 train_acc= 0.49351 val_loss= 0.78116 val_acc= 0.53226 time= 0.01563
Epoch: 0011 train_loss= 0.87373 train_acc= 0.52468 val_loss= 0.75451 val_acc= 0.50000 time= 0.00000
Epoch: 0012 train_loss= 0.82670 train_acc= 0.49870 val_loss= 0.72719 val_acc= 0.53226 time= 0.01563
Epoch: 0013 train_loss= 0.78351 train_acc= 0.48961 val_loss= 0.71171 val_acc= 0.50000 time= 0.01563
Epoch: 0014 train_loss= 1.03515 train_acc= 0.49221 val_loss= 0.70139 val_acc= 0.53226 time= 0.01563
Epoch: 0015 train_loss= 0.87615 train_acc= 0.50130 val_loss= 0.69769 val_acc= 0.51613 time= 0.01562
Epoch: 0016 train_loss= 0.90558 train_acc= 0.48961 val_loss= 0.70219 val_acc= 0.54839 time= 0.01563
Epoch: 0017 train_loss= 1.14177 train_acc= 0.49740 val_loss= 0.70773 val_acc= 0.58065 time= 0.00000
Epoch: 0018 train_loss= 0.82445 train_acc= 0.48701 val_loss= 0.71315 val_acc= 0.58065 time= 0.01563
Epoch: 0019 train_loss= 0.90610 train_acc= 0.48182 val_loss= 0.71400 val_acc= 0.58065 time= 0.01563
Epoch: 0020 train_loss= 0.73680 train_acc= 0.50390 val_loss= 0.71388 val_acc= 0.58065 time= 0.01563
Epoch: 0021 train_loss= 0.84462 train_acc= 0.52857 val_loss= 0.71382 val_acc= 0.58065 time= 0.01562
Epoch: 0022 train_loss= 1.09516 train_acc= 0.49740 val_loss= 0.70637 val_acc= 0.58065 time= 0.01563
Epoch: 0023 train_loss= 1.04688 train_acc= 0.50519 val_loss= 0.69942 val_acc= 0.58065 time= 0.00000
Epoch: 0024 train_loss= 0.90572 train_acc= 0.48442 val_loss= 0.69500 val_acc= 0.58065 time= 0.01563
Epoch: 0025 train_loss= 0.78888 train_acc= 0.51818 val_loss= 0.69390 val_acc= 0.54839 time= 0.01563
Epoch: 0026 train_loss= 0.88144 train_acc= 0.49870 val_loss= 0.69572 val_acc= 0.51613 time= 0.01562
Epoch: 0027 train_loss= 0.81909 train_acc= 0.51429 val_loss= 0.70201 val_acc= 0.50000 time= 0.01563
Epoch: 0028 train_loss= 0.77801 train_acc= 0.47922 val_loss= 0.71113 val_acc= 0.41935 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69607 accuracy= 0.50806 time= 0.00000 
