Epoch: 0001 train_loss= 0.70109 train_acc= 0.48831 val_loss= 0.69887 val_acc= 0.42623 time= 0.35941
Epoch: 0002 train_loss= 0.69796 train_acc= 0.52078 val_loss= 0.69753 val_acc= 0.42623 time= 0.01562
Epoch: 0003 train_loss= 0.69566 train_acc= 0.51948 val_loss= 0.69695 val_acc= 0.42623 time= 0.01563
Epoch: 0004 train_loss= 0.69415 train_acc= 0.51948 val_loss= 0.69681 val_acc= 0.42623 time= 0.00000
Epoch: 0005 train_loss= 0.69327 train_acc= 0.51948 val_loss= 0.69686 val_acc= 0.42623 time= 0.01563
Epoch: 0006 train_loss= 0.69280 train_acc= 0.51948 val_loss= 0.69697 val_acc= 0.42623 time= 0.01563
Epoch: 0007 train_loss= 0.69239 train_acc= 0.52078 val_loss= 0.69703 val_acc= 0.42623 time= 0.01563
Epoch: 0008 train_loss= 0.69249 train_acc= 0.51948 val_loss= 0.69701 val_acc= 0.42623 time= 0.00000
Epoch: 0009 train_loss= 0.69232 train_acc= 0.51948 val_loss= 0.69698 val_acc= 0.42623 time= 0.01563
Epoch: 0010 train_loss= 0.69226 train_acc= 0.52078 val_loss= 0.69679 val_acc= 0.42623 time= 0.01563
Epoch: 0011 train_loss= 0.69232 train_acc= 0.52078 val_loss= 0.69651 val_acc= 0.42623 time= 0.00000
Epoch: 0012 train_loss= 0.69218 train_acc= 0.52597 val_loss= 0.69639 val_acc= 0.42623 time= 0.01563
Epoch: 0013 train_loss= 0.69199 train_acc= 0.52078 val_loss= 0.69636 val_acc= 0.42623 time= 0.01563
Epoch: 0014 train_loss= 0.69202 train_acc= 0.52078 val_loss= 0.69639 val_acc= 0.42623 time= 0.01563
Epoch: 0015 train_loss= 0.69151 train_acc= 0.52597 val_loss= 0.69638 val_acc= 0.42623 time= 0.00000
Epoch: 0016 train_loss= 0.69109 train_acc= 0.52727 val_loss= 0.69608 val_acc= 0.42623 time= 0.01563
Epoch: 0017 train_loss= 0.69097 train_acc= 0.52857 val_loss= 0.69572 val_acc= 0.42623 time= 0.01563
Epoch: 0018 train_loss= 0.69103 train_acc= 0.52727 val_loss= 0.69518 val_acc= 0.42623 time= 0.00000
Epoch: 0019 train_loss= 0.69094 train_acc= 0.53506 val_loss= 0.69458 val_acc= 0.42623 time= 0.01563
Epoch: 0020 train_loss= 0.69030 train_acc= 0.54286 val_loss= 0.69424 val_acc= 0.42623 time= 0.01563
Epoch: 0021 train_loss= 0.69058 train_acc= 0.54545 val_loss= 0.69409 val_acc= 0.42623 time= 0.01563
Epoch: 0022 train_loss= 0.69021 train_acc= 0.54026 val_loss= 0.69416 val_acc= 0.42623 time= 0.00000
Epoch: 0023 train_loss= 0.69021 train_acc= 0.54416 val_loss= 0.69428 val_acc= 0.42623 time= 0.01563
Epoch: 0024 train_loss= 0.69038 train_acc= 0.54286 val_loss= 0.69446 val_acc= 0.42623 time= 0.01563
Epoch: 0025 train_loss= 0.68961 train_acc= 0.54675 val_loss= 0.69437 val_acc= 0.42623 time= 0.01563
Epoch: 0026 train_loss= 0.68968 train_acc= 0.55195 val_loss= 0.69414 val_acc= 0.42623 time= 0.00000
Epoch: 0027 train_loss= 0.68911 train_acc= 0.55455 val_loss= 0.69404 val_acc= 0.42623 time= 0.01563
Epoch: 0028 train_loss= 0.68938 train_acc= 0.54286 val_loss= 0.69352 val_acc= 0.45902 time= 0.01563
Epoch: 0029 train_loss= 0.68970 train_acc= 0.54156 val_loss= 0.69237 val_acc= 0.45902 time= 0.01563
Epoch: 0030 train_loss= 0.68905 train_acc= 0.56104 val_loss= 0.69169 val_acc= 0.45902 time= 0.00000
Epoch: 0031 train_loss= 0.68862 train_acc= 0.56753 val_loss= 0.69201 val_acc= 0.45902 time= 0.01563
Epoch: 0032 train_loss= 0.68899 train_acc= 0.57143 val_loss= 0.69303 val_acc= 0.45902 time= 0.01563
Epoch: 0033 train_loss= 0.68896 train_acc= 0.54675 val_loss= 0.69347 val_acc= 0.45902 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68725 accuracy= 0.55738 time= 0.01563 
