Epoch: 0001 train_loss= 1.39426 train_acc= 0.28339 val_loss= 1.39079 val_acc= 0.30357 time= 0.16929
Epoch: 0002 train_loss= 1.39094 train_acc= 0.31596 val_loss= 1.38788 val_acc= 0.30357 time= 0.01716
Epoch: 0003 train_loss= 1.38807 train_acc= 0.31270 val_loss= 1.38556 val_acc= 0.30357 time= 0.00506
Epoch: 0004 train_loss= 1.38578 train_acc= 0.30945 val_loss= 1.38378 val_acc= 0.30357 time= 0.01562
Epoch: 0005 train_loss= 1.38378 train_acc= 0.30945 val_loss= 1.38250 val_acc= 0.30357 time= 0.00000
Epoch: 0006 train_loss= 1.38265 train_acc= 0.30945 val_loss= 1.38166 val_acc= 0.30357 time= 0.01563
Epoch: 0007 train_loss= 1.38174 train_acc= 0.30945 val_loss= 1.38124 val_acc= 0.30357 time= 0.01563
Epoch: 0008 train_loss= 1.38043 train_acc= 0.30945 val_loss= 1.38110 val_acc= 0.30357 time= 0.01563
Epoch: 0009 train_loss= 1.37970 train_acc= 0.30945 val_loss= 1.38108 val_acc= 0.30357 time= 0.00000
Epoch: 0010 train_loss= 1.38028 train_acc= 0.30945 val_loss= 1.38112 val_acc= 0.30357 time= 0.01563
Epoch: 0011 train_loss= 1.37955 train_acc= 0.30945 val_loss= 1.38109 val_acc= 0.30357 time= 0.01563
Epoch: 0012 train_loss= 1.37866 train_acc= 0.31270 val_loss= 1.38117 val_acc= 0.30357 time= 0.00000
Epoch: 0013 train_loss= 1.37872 train_acc= 0.30945 val_loss= 1.38122 val_acc= 0.30357 time= 0.01563
Epoch: 0014 train_loss= 1.37835 train_acc= 0.31270 val_loss= 1.38127 val_acc= 0.30357 time= 0.01563
Epoch: 0015 train_loss= 1.37845 train_acc= 0.31270 val_loss= 1.38129 val_acc= 0.30357 time= 0.00000
Epoch: 0016 train_loss= 1.37785 train_acc= 0.31270 val_loss= 1.38138 val_acc= 0.30357 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.38869 accuracy= 0.31858 time= 0.00000 
