Epoch: 0001 train_loss= 27.97314 train_acc= 0.46061 val_loss= 0.80842 val_acc= 0.40984 time= 0.14064
Epoch: 0002 train_loss= 10.46380 train_acc= 0.47879 val_loss= 0.76195 val_acc= 0.40984 time= 0.00000
Epoch: 0003 train_loss= 0.76410 train_acc= 0.50909 val_loss= 0.78673 val_acc= 0.45902 time= 0.01562
Epoch: 0004 train_loss= 0.87886 train_acc= 0.51818 val_loss= 0.85674 val_acc= 0.37705 time= 0.01563
Epoch: 0005 train_loss= 5.78132 train_acc= 0.46970 val_loss= 0.95998 val_acc= 0.42623 time= 0.00000
Epoch: 0006 train_loss= 1.60278 train_acc= 0.56364 val_loss= 1.05108 val_acc= 0.45902 time= 0.01563
Epoch: 0007 train_loss= 0.71834 train_acc= 0.56364 val_loss= 1.11637 val_acc= 0.47541 time= 0.00000
Epoch: 0008 train_loss= 4.39742 train_acc= 0.51818 val_loss= 1.11588 val_acc= 0.47541 time= 0.01563
Epoch: 0009 train_loss= 0.89477 train_acc= 0.53030 val_loss= 1.07283 val_acc= 0.49180 time= 0.01562
Epoch: 0010 train_loss= 0.77264 train_acc= 0.50606 val_loss= 1.03218 val_acc= 0.49180 time= 0.00000
Epoch: 0011 train_loss= 1.64702 train_acc= 0.51212 val_loss= 0.98633 val_acc= 0.49180 time= 0.01563
Epoch: 0012 train_loss= 0.84679 train_acc= 0.50909 val_loss= 0.94947 val_acc= 0.49180 time= 0.01563
Epoch: 0013 train_loss= 0.85126 train_acc= 0.53030 val_loss= 0.91299 val_acc= 0.49180 time= 0.00000
Epoch: 0014 train_loss= 0.79491 train_acc= 0.54545 val_loss= 0.87240 val_acc= 0.47541 time= 0.01563
Epoch: 0015 train_loss= 0.80526 train_acc= 0.54545 val_loss= 0.84654 val_acc= 0.49180 time= 0.01563
Epoch: 0016 train_loss= 0.84602 train_acc= 0.51212 val_loss= 0.82061 val_acc= 0.49180 time= 0.00000
Epoch: 0017 train_loss= 0.72520 train_acc= 0.55152 val_loss= 0.79036 val_acc= 0.47541 time= 0.01563
Epoch: 0018 train_loss= 0.87188 train_acc= 0.52121 val_loss= 0.76173 val_acc= 0.47541 time= 0.01563
Epoch: 0019 train_loss= 0.79036 train_acc= 0.52121 val_loss= 0.73789 val_acc= 0.45902 time= 0.00000
Epoch: 0020 train_loss= 0.79295 train_acc= 0.54848 val_loss= 0.72349 val_acc= 0.44262 time= 0.01563
Epoch: 0021 train_loss= 0.75810 train_acc= 0.49697 val_loss= 0.71491 val_acc= 0.40984 time= 0.01563
Epoch: 0022 train_loss= 0.75311 train_acc= 0.50909 val_loss= 0.71050 val_acc= 0.42623 time= 0.00000
Epoch: 0023 train_loss= 0.86765 train_acc= 0.48788 val_loss= 0.71012 val_acc= 0.44262 time= 0.01563
Epoch: 0024 train_loss= 2.10084 train_acc= 0.55455 val_loss= 0.71044 val_acc= 0.40984 time= 0.01563
Epoch: 0025 train_loss= 0.72035 train_acc= 0.53939 val_loss= 0.71118 val_acc= 0.40984 time= 0.01562
Epoch: 0026 train_loss= 0.79170 train_acc= 0.53636 val_loss= 0.71285 val_acc= 0.40984 time= 0.00000
Epoch: 0027 train_loss= 0.76948 train_acc= 0.50303 val_loss= 0.71564 val_acc= 0.40984 time= 0.01562
Epoch: 0028 train_loss= 2.00118 train_acc= 0.48485 val_loss= 0.72101 val_acc= 0.47541 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.79092 accuracy= 0.50820 time= 0.00000 
