Epoch: 0001 train_loss= 0.69794 train_acc= 0.55455 val_loss= 0.69954 val_acc= 0.49180 time= 0.10985
Epoch: 0002 train_loss= 0.69615 train_acc= 0.55758 val_loss= 0.69984 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69578 train_acc= 0.55758 val_loss= 0.70040 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.69490 train_acc= 0.55758 val_loss= 0.70141 val_acc= 0.49180 time= 0.01563
Epoch: 0005 train_loss= 0.69458 train_acc= 0.55758 val_loss= 0.70254 val_acc= 0.49180 time= 0.00000
Epoch: 0006 train_loss= 0.69374 train_acc= 0.55758 val_loss= 0.70360 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69467 train_acc= 0.55758 val_loss= 0.70418 val_acc= 0.49180 time= 0.00000
Epoch: 0008 train_loss= 0.69311 train_acc= 0.55758 val_loss= 0.70441 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 0.69306 train_acc= 0.55758 val_loss= 0.70437 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.69380 train_acc= 0.55758 val_loss= 0.70376 val_acc= 0.49180 time= 0.01563
Epoch: 0011 train_loss= 0.69249 train_acc= 0.55758 val_loss= 0.70294 val_acc= 0.49180 time= 0.01563
Epoch: 0012 train_loss= 0.69246 train_acc= 0.55758 val_loss= 0.70199 val_acc= 0.49180 time= 0.00000
Epoch: 0013 train_loss= 0.69229 train_acc= 0.55758 val_loss= 0.70106 val_acc= 0.49180 time= 0.01563
Epoch: 0014 train_loss= 0.69167 train_acc= 0.55758 val_loss= 0.70023 val_acc= 0.49180 time= 0.01563
Epoch: 0015 train_loss= 0.69231 train_acc= 0.55758 val_loss= 0.69957 val_acc= 0.49180 time= 0.01563
Epoch: 0016 train_loss= 0.69142 train_acc= 0.55758 val_loss= 0.69910 val_acc= 0.49180 time= 0.00000
Epoch: 0017 train_loss= 0.69040 train_acc= 0.55758 val_loss= 0.69879 val_acc= 0.49180 time= 0.01563
Epoch: 0018 train_loss= 0.69080 train_acc= 0.55758 val_loss= 0.69860 val_acc= 0.49180 time= 0.01563
Epoch: 0019 train_loss= 0.69096 train_acc= 0.55758 val_loss= 0.69848 val_acc= 0.49180 time= 0.01563
Epoch: 0020 train_loss= 0.69145 train_acc= 0.55758 val_loss= 0.69840 val_acc= 0.49180 time= 0.01563
Epoch: 0021 train_loss= 0.69138 train_acc= 0.55758 val_loss= 0.69838 val_acc= 0.49180 time= 0.00000
Epoch: 0022 train_loss= 0.69079 train_acc= 0.55758 val_loss= 0.69847 val_acc= 0.49180 time= 0.01563
Epoch: 0023 train_loss= 0.69097 train_acc= 0.55758 val_loss= 0.69864 val_acc= 0.49180 time= 0.01563
Epoch: 0024 train_loss= 0.69114 train_acc= 0.55758 val_loss= 0.69884 val_acc= 0.49180 time= 0.01563
Epoch: 0025 train_loss= 0.69067 train_acc= 0.55758 val_loss= 0.69903 val_acc= 0.49180 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69455 accuracy= 0.53279 time= 0.01563 
