Epoch: 0001 train_loss= 0.69949 train_acc= 0.49221 val_loss= 0.69937 val_acc= 0.44262 time= 0.70317
Epoch: 0002 train_loss= 0.69893 train_acc= 0.47922 val_loss= 0.69811 val_acc= 0.55738 time= 0.01563
Epoch: 0003 train_loss= 0.69827 train_acc= 0.50130 val_loss= 0.69720 val_acc= 0.55738 time= 0.00000
Epoch: 0004 train_loss= 0.69752 train_acc= 0.51039 val_loss= 0.69650 val_acc= 0.55738 time= 0.01563
Epoch: 0005 train_loss= 0.69753 train_acc= 0.49610 val_loss= 0.69592 val_acc= 0.55738 time= 0.01563
Epoch: 0006 train_loss= 0.69712 train_acc= 0.50909 val_loss= 0.69551 val_acc= 0.55738 time= 0.01563
Epoch: 0007 train_loss= 0.69639 train_acc= 0.50390 val_loss= 0.69519 val_acc= 0.55738 time= 0.01563
Epoch: 0008 train_loss= 0.69619 train_acc= 0.50260 val_loss= 0.69490 val_acc= 0.55738 time= 0.00000
Epoch: 0009 train_loss= 0.69591 train_acc= 0.50779 val_loss= 0.69463 val_acc= 0.55738 time= 0.01563
Epoch: 0010 train_loss= 0.69537 train_acc= 0.51429 val_loss= 0.69441 val_acc= 0.55738 time= 0.01562
Epoch: 0011 train_loss= 0.69523 train_acc= 0.50909 val_loss= 0.69425 val_acc= 0.55738 time= 0.01563
Epoch: 0012 train_loss= 0.69494 train_acc= 0.51818 val_loss= 0.69412 val_acc= 0.55738 time= 0.01563
Epoch: 0013 train_loss= 0.69466 train_acc= 0.51169 val_loss= 0.69401 val_acc= 0.55738 time= 0.00000
Epoch: 0014 train_loss= 0.69449 train_acc= 0.51558 val_loss= 0.69390 val_acc= 0.55738 time= 0.01563
Epoch: 0015 train_loss= 0.69434 train_acc= 0.50130 val_loss= 0.69382 val_acc= 0.55738 time= 0.01563
Epoch: 0016 train_loss= 0.69421 train_acc= 0.49610 val_loss= 0.69378 val_acc= 0.55738 time= 0.01563
Epoch: 0017 train_loss= 0.69398 train_acc= 0.51039 val_loss= 0.69371 val_acc= 0.55738 time= 0.01563
Epoch: 0018 train_loss= 0.69402 train_acc= 0.50390 val_loss= 0.69363 val_acc= 0.55738 time= 0.00000
Epoch: 0019 train_loss= 0.69381 train_acc= 0.51429 val_loss= 0.69354 val_acc= 0.55738 time= 0.01563
Epoch: 0020 train_loss= 0.69383 train_acc= 0.49870 val_loss= 0.69346 val_acc= 0.55738 time= 0.01563
Epoch: 0021 train_loss= 0.69359 train_acc= 0.50260 val_loss= 0.69341 val_acc= 0.55738 time= 0.01631
Epoch: 0022 train_loss= 0.69355 train_acc= 0.49870 val_loss= 0.69334 val_acc= 0.55738 time= 0.01640
Epoch: 0023 train_loss= 0.69353 train_acc= 0.50130 val_loss= 0.69326 val_acc= 0.55738 time= 0.01563
Epoch: 0024 train_loss= 0.69357 train_acc= 0.49870 val_loss= 0.69322 val_acc= 0.55738 time= 0.00000
Epoch: 0025 train_loss= 0.69339 train_acc= 0.51429 val_loss= 0.69316 val_acc= 0.55738 time= 0.01563
Epoch: 0026 train_loss= 0.69338 train_acc= 0.51558 val_loss= 0.69312 val_acc= 0.55738 time= 0.01563
Epoch: 0027 train_loss= 0.69332 train_acc= 0.51818 val_loss= 0.69308 val_acc= 0.55738 time= 0.01563
Epoch: 0028 train_loss= 0.69332 train_acc= 0.50649 val_loss= 0.69305 val_acc= 0.55738 time= 0.01563
Epoch: 0029 train_loss= 0.69331 train_acc= 0.50519 val_loss= 0.69303 val_acc= 0.55738 time= 0.00000
Epoch: 0030 train_loss= 0.69327 train_acc= 0.50779 val_loss= 0.69302 val_acc= 0.55738 time= 0.01563
Epoch: 0031 train_loss= 0.69327 train_acc= 0.51039 val_loss= 0.69301 val_acc= 0.55738 time= 0.01563
Epoch: 0032 train_loss= 0.69324 train_acc= 0.51039 val_loss= 0.69299 val_acc= 0.55738 time= 0.01563
Epoch: 0033 train_loss= 0.69320 train_acc= 0.51818 val_loss= 0.69294 val_acc= 0.55738 time= 0.01562
Epoch: 0034 train_loss= 0.69325 train_acc= 0.50909 val_loss= 0.69292 val_acc= 0.55738 time= 0.00000
Epoch: 0035 train_loss= 0.69322 train_acc= 0.51169 val_loss= 0.69291 val_acc= 0.55738 time= 0.01563
Epoch: 0036 train_loss= 0.69322 train_acc= 0.51039 val_loss= 0.69290 val_acc= 0.55738 time= 0.01563
Epoch: 0037 train_loss= 0.69322 train_acc= 0.51169 val_loss= 0.69292 val_acc= 0.55738 time= 0.00000
Epoch: 0038 train_loss= 0.69323 train_acc= 0.50649 val_loss= 0.69298 val_acc= 0.55738 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.69334 accuracy= 0.46721 time= 0.01842 
