Epoch: 0001 train_loss= 1.39281 train_acc= 0.18750 val_loss= 1.39223 val_acc= 0.25000 time= 0.45320
Epoch: 0002 train_loss= 1.39025 train_acc= 0.30469 val_loss= 1.39156 val_acc= 0.25000 time= 0.01594
Epoch: 0003 train_loss= 1.38840 train_acc= 0.30664 val_loss= 1.39136 val_acc= 0.25000 time= 0.01563
Epoch: 0004 train_loss= 1.38675 train_acc= 0.30664 val_loss= 1.39128 val_acc= 0.25000 time= 0.01563
Epoch: 0005 train_loss= 1.38509 train_acc= 0.30664 val_loss= 1.39135 val_acc= 0.25000 time= 0.01563
Epoch: 0006 train_loss= 1.38408 train_acc= 0.30664 val_loss= 1.39164 val_acc= 0.25000 time= 0.01563
Epoch: 0007 train_loss= 1.38148 train_acc= 0.30859 val_loss= 1.39214 val_acc= 0.25000 time= 0.00000
Epoch: 0008 train_loss= 1.38150 train_acc= 0.30664 val_loss= 1.39275 val_acc= 0.25000 time= 0.03125
Epoch: 0009 train_loss= 1.38021 train_acc= 0.30469 val_loss= 1.39340 val_acc= 0.25000 time= 0.01563
Epoch: 0010 train_loss= 1.37917 train_acc= 0.30664 val_loss= 1.39402 val_acc= 0.25000 time= 0.00000
Epoch: 0011 train_loss= 1.37828 train_acc= 0.30664 val_loss= 1.39460 val_acc= 0.25000 time= 0.01563
Epoch: 0012 train_loss= 1.37852 train_acc= 0.30469 val_loss= 1.39503 val_acc= 0.25000 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.37355 accuracy= 0.31667 time= 0.01563 
