Epoch: 0001 train_loss= 0.69909 train_acc= 0.51455 val_loss= 0.70134 val_acc= 0.49180 time= 0.54931
Epoch: 0002 train_loss= 0.69918 train_acc= 0.50182 val_loss= 0.70003 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69847 train_acc= 0.49273 val_loss= 0.69905 val_acc= 0.50820 time= 0.01563
Epoch: 0004 train_loss= 0.69755 train_acc= 0.51273 val_loss= 0.69813 val_acc= 0.50820 time= 0.00000
Epoch: 0005 train_loss= 0.69695 train_acc= 0.51091 val_loss= 0.69752 val_acc= 0.50820 time= 0.00000
Epoch: 0006 train_loss= 0.69697 train_acc= 0.51091 val_loss= 0.69715 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69727 train_acc= 0.48364 val_loss= 0.69704 val_acc= 0.49180 time= 0.00000
Epoch: 0008 train_loss= 0.69571 train_acc= 0.50545 val_loss= 0.69701 val_acc= 0.50820 time= 0.00000
Epoch: 0009 train_loss= 0.69594 train_acc= 0.52364 val_loss= 0.69704 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.69463 train_acc= 0.50364 val_loss= 0.69715 val_acc= 0.45902 time= 0.00000
Epoch: 0011 train_loss= 0.69480 train_acc= 0.53818 val_loss= 0.69693 val_acc= 0.50820 time= 0.00000
Epoch: 0012 train_loss= 0.69374 train_acc= 0.53818 val_loss= 0.69673 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 0.69376 train_acc= 0.50909 val_loss= 0.69641 val_acc= 0.55738 time= 0.00000
Epoch: 0014 train_loss= 0.69443 train_acc= 0.49273 val_loss= 0.69600 val_acc= 0.49180 time= 0.01810
Epoch: 0015 train_loss= 0.69345 train_acc= 0.54727 val_loss= 0.69560 val_acc= 0.50820 time= 0.00303
Epoch: 0016 train_loss= 0.69386 train_acc= 0.51455 val_loss= 0.69510 val_acc= 0.49180 time= 0.00000
Epoch: 0017 train_loss= 0.69264 train_acc= 0.54000 val_loss= 0.69493 val_acc= 0.49180 time= 0.01050
Epoch: 0018 train_loss= 0.69330 train_acc= 0.51091 val_loss= 0.69472 val_acc= 0.49180 time= 0.00000
Epoch: 0019 train_loss= 0.69348 train_acc= 0.48909 val_loss= 0.69465 val_acc= 0.49180 time= 0.00000
Epoch: 0020 train_loss= 0.69247 train_acc= 0.51273 val_loss= 0.69464 val_acc= 0.49180 time= 0.01563
Epoch: 0021 train_loss= 0.69240 train_acc= 0.53455 val_loss= 0.69474 val_acc= 0.49180 time= 0.00000
Epoch: 0022 train_loss= 0.69195 train_acc= 0.53091 val_loss= 0.69517 val_acc= 0.50820 time= 0.01563
Epoch: 0023 train_loss= 0.69304 train_acc= 0.52727 val_loss= 0.69546 val_acc= 0.50820 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69451 accuracy= 0.53279 time= 0.00000 
