Epoch: 0001 train_loss= 0.69945 train_acc= 0.46753 val_loss= 0.69861 val_acc= 0.50820 time= 0.70318
Epoch: 0002 train_loss= 0.69873 train_acc= 0.54935 val_loss= 0.69776 val_acc= 0.50820 time= 0.01562
Epoch: 0003 train_loss= 0.69780 train_acc= 0.53766 val_loss= 0.69704 val_acc= 0.50820 time= 0.01563
Epoch: 0004 train_loss= 0.69727 train_acc= 0.53896 val_loss= 0.69637 val_acc= 0.50820 time= 0.00000
Epoch: 0005 train_loss= 0.69680 train_acc= 0.53506 val_loss= 0.69576 val_acc= 0.50820 time= 0.01563
Epoch: 0006 train_loss= 0.69634 train_acc= 0.53636 val_loss= 0.69520 val_acc= 0.50820 time= 0.01562
Epoch: 0007 train_loss= 0.69561 train_acc= 0.53766 val_loss= 0.69471 val_acc= 0.50820 time= 0.01563
Epoch: 0008 train_loss= 0.69493 train_acc= 0.53766 val_loss= 0.69429 val_acc= 0.50820 time= 0.01563
Epoch: 0009 train_loss= 0.69471 train_acc= 0.53766 val_loss= 0.69392 val_acc= 0.50820 time= 0.00000
Epoch: 0010 train_loss= 0.69452 train_acc= 0.53506 val_loss= 0.69361 val_acc= 0.50820 time= 0.01563
Epoch: 0011 train_loss= 0.69391 train_acc= 0.53766 val_loss= 0.69334 val_acc= 0.50820 time= 0.01563
Epoch: 0012 train_loss= 0.69445 train_acc= 0.53377 val_loss= 0.69310 val_acc= 0.50820 time= 0.01563
Epoch: 0013 train_loss= 0.69386 train_acc= 0.53636 val_loss= 0.69289 val_acc= 0.50820 time= 0.01563
Epoch: 0014 train_loss= 0.69345 train_acc= 0.53766 val_loss= 0.69271 val_acc= 0.50820 time= 0.01562
Epoch: 0015 train_loss= 0.69325 train_acc= 0.53506 val_loss= 0.69254 val_acc= 0.50820 time= 0.00000
Epoch: 0016 train_loss= 0.69372 train_acc= 0.53506 val_loss= 0.69243 val_acc= 0.50820 time= 0.01563
Epoch: 0017 train_loss= 0.69341 train_acc= 0.53506 val_loss= 0.69236 val_acc= 0.50820 time= 0.02172
Epoch: 0018 train_loss= 0.69318 train_acc= 0.53247 val_loss= 0.69233 val_acc= 0.50820 time= 0.01000
Epoch: 0019 train_loss= 0.69289 train_acc= 0.53377 val_loss= 0.69229 val_acc= 0.50820 time= 0.01563
Epoch: 0020 train_loss= 0.69333 train_acc= 0.53506 val_loss= 0.69225 val_acc= 0.50820 time= 0.01563
Epoch: 0021 train_loss= 0.69270 train_acc= 0.54026 val_loss= 0.69219 val_acc= 0.50820 time= 0.01562
Epoch: 0022 train_loss= 0.69279 train_acc= 0.54286 val_loss= 0.69210 val_acc= 0.50820 time= 0.00000
Epoch: 0023 train_loss= 0.69251 train_acc= 0.53896 val_loss= 0.69199 val_acc= 0.50820 time= 0.01563
Epoch: 0024 train_loss= 0.69287 train_acc= 0.53506 val_loss= 0.69187 val_acc= 0.50820 time= 0.01563
Epoch: 0025 train_loss= 0.69227 train_acc= 0.53766 val_loss= 0.69176 val_acc= 0.50820 time= 0.01562
Epoch: 0026 train_loss= 0.69206 train_acc= 0.53766 val_loss= 0.69164 val_acc= 0.50820 time= 0.01563
Epoch: 0027 train_loss= 0.69207 train_acc= 0.53766 val_loss= 0.69155 val_acc= 0.50820 time= 0.00000
Epoch: 0028 train_loss= 0.69283 train_acc= 0.53636 val_loss= 0.69150 val_acc= 0.50820 time= 0.01563
Epoch: 0029 train_loss= 0.69235 train_acc= 0.53377 val_loss= 0.69147 val_acc= 0.50820 time= 0.01563
Epoch: 0030 train_loss= 0.69239 train_acc= 0.53636 val_loss= 0.69145 val_acc= 0.50820 time= 0.01563
Epoch: 0031 train_loss= 0.69297 train_acc= 0.53636 val_loss= 0.69144 val_acc= 0.50820 time= 0.01563
Epoch: 0032 train_loss= 0.69236 train_acc= 0.53636 val_loss= 0.69145 val_acc= 0.50820 time= 0.01563
Epoch: 0033 train_loss= 0.69243 train_acc= 0.53636 val_loss= 0.69147 val_acc= 0.50820 time= 0.01563
Epoch: 0034 train_loss= 0.69217 train_acc= 0.53636 val_loss= 0.69149 val_acc= 0.50820 time= 0.01563
Epoch: 0035 train_loss= 0.69233 train_acc= 0.53636 val_loss= 0.69151 val_acc= 0.50820 time= 0.01563
Epoch: 0036 train_loss= 0.69214 train_acc= 0.53636 val_loss= 0.69153 val_acc= 0.50820 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69007 accuracy= 0.54918 time= 0.01563 
