Epoch: 0001 train_loss= 0.80647 train_acc= 0.53636 val_loss= 0.80933 val_acc= 0.55738 time= 0.31252
Epoch: 0002 train_loss= 0.82087 train_acc= 0.52424 val_loss= 0.75399 val_acc= 0.55738 time= 0.01563
Epoch: 0003 train_loss= 0.84853 train_acc= 0.49394 val_loss= 0.78074 val_acc= 0.42623 time= 0.03125
Epoch: 0004 train_loss= 0.90713 train_acc= 0.50303 val_loss= 0.83231 val_acc= 0.44262 time= 0.01563
Epoch: 0005 train_loss= 0.79103 train_acc= 0.46667 val_loss= 0.86936 val_acc= 0.45902 time= 0.03125
Epoch: 0006 train_loss= 0.80632 train_acc= 0.49394 val_loss= 0.86227 val_acc= 0.44262 time= 0.01563
Epoch: 0007 train_loss= 0.75899 train_acc= 0.56970 val_loss= 0.82716 val_acc= 0.45902 time= 0.03125
Epoch: 0008 train_loss= 0.69321 train_acc= 0.51212 val_loss= 0.79535 val_acc= 0.47541 time= 0.01563
Epoch: 0009 train_loss= 0.79063 train_acc= 0.49091 val_loss= 0.76361 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.70947 train_acc= 0.55455 val_loss= 0.74807 val_acc= 0.42623 time= 0.01562
Epoch: 0011 train_loss= 0.70802 train_acc= 0.53636 val_loss= 0.73661 val_acc= 0.42623 time= 0.03125
Epoch: 0012 train_loss= 0.70043 train_acc= 0.54242 val_loss= 0.72690 val_acc= 0.37705 time= 0.01562
Epoch: 0013 train_loss= 0.71810 train_acc= 0.53939 val_loss= 0.72054 val_acc= 0.39344 time= 0.01563
Epoch: 0014 train_loss= 0.70996 train_acc= 0.53030 val_loss= 0.71699 val_acc= 0.42623 time= 0.03125
Epoch: 0015 train_loss= 0.70366 train_acc= 0.53939 val_loss= 0.71489 val_acc= 0.44262 time= 0.01563
Epoch: 0016 train_loss= 0.68716 train_acc= 0.52727 val_loss= 0.71409 val_acc= 0.44262 time= 0.01562
Epoch: 0017 train_loss= 0.68989 train_acc= 0.55758 val_loss= 0.71338 val_acc= 0.44262 time= 0.01563
Epoch: 0018 train_loss= 0.67721 train_acc= 0.55152 val_loss= 0.71309 val_acc= 0.44262 time= 0.03125
Epoch: 0019 train_loss= 0.67938 train_acc= 0.56970 val_loss= 0.71319 val_acc= 0.44262 time= 0.01563
Epoch: 0020 train_loss= 0.69678 train_acc= 0.52727 val_loss= 0.71306 val_acc= 0.44262 time= 0.01563
Epoch: 0021 train_loss= 0.68677 train_acc= 0.51515 val_loss= 0.71337 val_acc= 0.44262 time= 0.01563
Epoch: 0022 train_loss= 0.68316 train_acc= 0.54545 val_loss= 0.71371 val_acc= 0.44262 time= 0.03125
Epoch: 0023 train_loss= 0.67129 train_acc= 0.58788 val_loss= 0.71445 val_acc= 0.44262 time= 0.01563
Epoch: 0024 train_loss= 0.68789 train_acc= 0.58485 val_loss= 0.71508 val_acc= 0.45902 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.70167 accuracy= 0.51639 time= 0.01563 
