Epoch: 0001 train_loss= 1.40262 train_acc= 0.26059 val_loss= 1.40032 val_acc= 0.16071 time= 0.12501
Epoch: 0002 train_loss= 1.40709 train_acc= 0.26059 val_loss= 1.38884 val_acc= 0.25000 time= 0.00494
Epoch: 0003 train_loss= 1.39070 train_acc= 0.28339 val_loss= 1.38028 val_acc= 0.35714 time= 0.01100
Epoch: 0004 train_loss= 1.38807 train_acc= 0.28339 val_loss= 1.37614 val_acc= 0.28571 time= 0.01563
Epoch: 0005 train_loss= 1.39953 train_acc= 0.27362 val_loss= 1.37250 val_acc= 0.26786 time= 0.01563
Epoch: 0006 train_loss= 1.39016 train_acc= 0.28990 val_loss= 1.36921 val_acc= 0.28571 time= 0.00000
Epoch: 0007 train_loss= 1.39525 train_acc= 0.29316 val_loss= 1.36921 val_acc= 0.30357 time= 0.01563
Epoch: 0008 train_loss= 1.40292 train_acc= 0.27687 val_loss= 1.36950 val_acc= 0.28571 time= 0.01562
Epoch: 0009 train_loss= 1.37943 train_acc= 0.32899 val_loss= 1.36928 val_acc= 0.32143 time= 0.01563
Epoch: 0010 train_loss= 1.38544 train_acc= 0.35505 val_loss= 1.37014 val_acc= 0.33929 time= 0.01563
Epoch: 0011 train_loss= 1.39092 train_acc= 0.29642 val_loss= 1.37090 val_acc= 0.32143 time= 0.00000
Epoch: 0012 train_loss= 1.38791 train_acc= 0.27036 val_loss= 1.37209 val_acc= 0.30357 time= 0.01563
Epoch: 0013 train_loss= 1.40468 train_acc= 0.27687 val_loss= 1.37351 val_acc= 0.30357 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38309 accuracy= 0.36283 time= 0.00000 
