Epoch: 0001 train_loss= 1.76955 train_acc= 0.26562 val_loss= 1.44860 val_acc= 0.26786 time= 0.64072
Epoch: 0002 train_loss= 1.59163 train_acc= 0.27148 val_loss= 1.60666 val_acc= 0.19643 time= 0.03125
Epoch: 0003 train_loss= 1.95480 train_acc= 0.27148 val_loss= 1.52924 val_acc= 0.21429 time= 0.01563
Epoch: 0004 train_loss= 1.72946 train_acc= 0.22461 val_loss= 1.46161 val_acc= 0.28571 time= 0.01563
Epoch: 0005 train_loss= 1.81871 train_acc= 0.27734 val_loss= 1.45134 val_acc= 0.33929 time= 0.03125
Epoch: 0006 train_loss= 1.40152 train_acc= 0.28711 val_loss= 1.44579 val_acc= 0.32143 time= 0.01563
Epoch: 0007 train_loss= 1.48497 train_acc= 0.29688 val_loss= 1.45041 val_acc= 0.30357 time= 0.03125
Epoch: 0008 train_loss= 1.60137 train_acc= 0.25977 val_loss= 1.43348 val_acc= 0.26786 time= 0.01563
Epoch: 0009 train_loss= 1.43911 train_acc= 0.29102 val_loss= 1.42385 val_acc= 0.28571 time= 0.03125
Epoch: 0010 train_loss= 1.38425 train_acc= 0.31055 val_loss= 1.42312 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.37463 train_acc= 0.31836 val_loss= 1.42387 val_acc= 0.28571 time= 0.03125
Epoch: 0012 train_loss= 1.39020 train_acc= 0.28906 val_loss= 1.42365 val_acc= 0.28571 time= 0.01563
Epoch: 0013 train_loss= 1.39667 train_acc= 0.28320 val_loss= 1.42436 val_acc= 0.28571 time= 0.01562
Epoch: 0014 train_loss= 1.46043 train_acc= 0.30664 val_loss= 1.42807 val_acc= 0.28571 time= 0.03125
Epoch: 0015 train_loss= 1.43445 train_acc= 0.28906 val_loss= 1.43135 val_acc= 0.26786 time= 0.01563
Epoch: 0016 train_loss= 1.38447 train_acc= 0.28711 val_loss= 1.43423 val_acc= 0.26786 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37188 accuracy= 0.29204 time= 0.01563 
