Epoch: 0001 train_loss= 0.88818 train_acc= 0.48961 val_loss= 0.73516 val_acc= 0.50000 time= 1.03211
Epoch: 0002 train_loss= 0.94400 train_acc= 0.50649 val_loss= 0.85989 val_acc= 0.53226 time= 0.03125
Epoch: 0003 train_loss= 0.99361 train_acc= 0.48442 val_loss= 0.80470 val_acc= 0.54839 time= 0.01563
Epoch: 0004 train_loss= 0.83850 train_acc= 0.51039 val_loss= 0.72422 val_acc= 0.54839 time= 0.03125
Epoch: 0005 train_loss= 0.76639 train_acc= 0.47792 val_loss= 0.70730 val_acc= 0.51613 time= 0.01563
Epoch: 0006 train_loss= 1.12533 train_acc= 0.51039 val_loss= 0.75089 val_acc= 0.56452 time= 0.03125
Epoch: 0007 train_loss= 0.85663 train_acc= 0.51688 val_loss= 0.76121 val_acc= 0.54839 time= 0.03125
Epoch: 0008 train_loss= 0.77659 train_acc= 0.52727 val_loss= 0.75778 val_acc= 0.54839 time= 0.01563
Epoch: 0009 train_loss= 0.76717 train_acc= 0.49091 val_loss= 0.77232 val_acc= 0.54839 time= 0.03125
Epoch: 0010 train_loss= 1.11044 train_acc= 0.51429 val_loss= 0.75288 val_acc= 0.56452 time= 0.03125
Epoch: 0011 train_loss= 1.06223 train_acc= 0.51299 val_loss= 0.72126 val_acc= 0.56452 time= 0.01562
Epoch: 0012 train_loss= 0.84206 train_acc= 0.52208 val_loss= 0.70246 val_acc= 0.50000 time= 0.03125
Epoch: 0013 train_loss= 0.72703 train_acc= 0.50130 val_loss= 0.70315 val_acc= 0.53226 time= 0.03125
Epoch: 0014 train_loss= 0.84743 train_acc= 0.50519 val_loss= 0.70748 val_acc= 0.54839 time= 0.01563
Epoch: 0015 train_loss= 0.75826 train_acc= 0.52078 val_loss= 0.71401 val_acc= 0.54839 time= 0.03125
Epoch: 0016 train_loss= 0.75314 train_acc= 0.48701 val_loss= 0.70931 val_acc= 0.54839 time= 0.03125
Epoch: 0017 train_loss= 0.71535 train_acc= 0.50260 val_loss= 0.70596 val_acc= 0.54839 time= 0.03125
Epoch: 0018 train_loss= 1.04487 train_acc= 0.49221 val_loss= 0.70089 val_acc= 0.53226 time= 0.01563
Epoch: 0019 train_loss= 0.70946 train_acc= 0.55065 val_loss= 0.69854 val_acc= 0.51613 time= 0.03125
Epoch: 0020 train_loss= 0.83172 train_acc= 0.51299 val_loss= 0.70019 val_acc= 0.51613 time= 0.03125
Epoch: 0021 train_loss= 0.68992 train_acc= 0.53896 val_loss= 0.70120 val_acc= 0.51613 time= 0.01563
Epoch: 0022 train_loss= 0.69291 train_acc= 0.52338 val_loss= 0.70194 val_acc= 0.51613 time= 0.03125
Epoch: 0023 train_loss= 0.70573 train_acc= 0.50519 val_loss= 0.70257 val_acc= 0.51613 time= 0.01563
Epoch: 0024 train_loss= 0.70654 train_acc= 0.49351 val_loss= 0.70314 val_acc= 0.51613 time= 0.03125
Epoch: 0025 train_loss= 0.70546 train_acc= 0.49610 val_loss= 0.70370 val_acc= 0.51613 time= 0.03125
Epoch: 0026 train_loss= 0.69207 train_acc= 0.52468 val_loss= 0.70424 val_acc= 0.51613 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.72915 accuracy= 0.53226 time= 0.01562 
