Epoch: 0001 train_loss= 1.39229 train_acc= 0.31704 val_loss= 1.39151 val_acc= 0.28571 time= 0.32815
Epoch: 0002 train_loss= 1.39049 train_acc= 0.31844 val_loss= 1.39114 val_acc= 0.28571 time= 0.01563
Epoch: 0003 train_loss= 1.38946 train_acc= 0.31844 val_loss= 1.39072 val_acc= 0.28571 time= 0.01563
Epoch: 0004 train_loss= 1.38831 train_acc= 0.31844 val_loss= 1.39031 val_acc= 0.28571 time= 0.01563
Epoch: 0005 train_loss= 1.38675 train_acc= 0.31844 val_loss= 1.38996 val_acc= 0.28571 time= 0.01563
Epoch: 0006 train_loss= 1.38548 train_acc= 0.31844 val_loss= 1.38967 val_acc= 0.28571 time= 0.01563
Epoch: 0007 train_loss= 1.38408 train_acc= 0.31844 val_loss= 1.38947 val_acc= 0.28571 time= 0.01563
Epoch: 0008 train_loss= 1.38246 train_acc= 0.31844 val_loss= 1.38927 val_acc= 0.28571 time= 0.01563
Epoch: 0009 train_loss= 1.38105 train_acc= 0.31844 val_loss= 1.38910 val_acc= 0.28571 time= 0.01563
Epoch: 0010 train_loss= 1.37915 train_acc= 0.31844 val_loss= 1.38901 val_acc= 0.28571 time= 0.01563
Epoch: 0011 train_loss= 1.37819 train_acc= 0.31844 val_loss= 1.38902 val_acc= 0.28571 time= 0.01563
Epoch: 0012 train_loss= 1.37686 train_acc= 0.31844 val_loss= 1.38914 val_acc= 0.28571 time= 0.01563
Epoch: 0013 train_loss= 1.37548 train_acc= 0.31844 val_loss= 1.38939 val_acc= 0.28571 time= 0.01563
Epoch: 0014 train_loss= 1.37524 train_acc= 0.31844 val_loss= 1.38976 val_acc= 0.28571 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38184 accuracy= 0.30088 time= 0.01563 
