Epoch: 0001 train_loss= 0.69949 train_acc= 0.48052 val_loss= 0.69899 val_acc= 0.36066 time= 0.62014
Epoch: 0002 train_loss= 0.69888 train_acc= 0.49870 val_loss= 0.69781 val_acc= 0.63934 time= 0.01200
Epoch: 0003 train_loss= 0.69827 train_acc= 0.51299 val_loss= 0.69720 val_acc= 0.63934 time= 0.01300
Epoch: 0004 train_loss= 0.69794 train_acc= 0.49221 val_loss= 0.69682 val_acc= 0.63934 time= 0.01300
Epoch: 0005 train_loss= 0.69732 train_acc= 0.50519 val_loss= 0.69640 val_acc= 0.63934 time= 0.01500
Epoch: 0006 train_loss= 0.69692 train_acc= 0.51688 val_loss= 0.69584 val_acc= 0.63934 time= 0.01200
Epoch: 0007 train_loss= 0.69646 train_acc= 0.51818 val_loss= 0.69543 val_acc= 0.63934 time= 0.01400
Epoch: 0008 train_loss= 0.69614 train_acc= 0.52597 val_loss= 0.69516 val_acc= 0.63934 time= 0.01500
Epoch: 0009 train_loss= 0.69582 train_acc= 0.50000 val_loss= 0.69489 val_acc= 0.63934 time= 0.01500
Epoch: 0010 train_loss= 0.69545 train_acc= 0.52468 val_loss= 0.69474 val_acc= 0.63934 time= 0.01500
Epoch: 0011 train_loss= 0.69537 train_acc= 0.49610 val_loss= 0.69449 val_acc= 0.63934 time= 0.01500
Epoch: 0012 train_loss= 0.69500 train_acc= 0.50909 val_loss= 0.69408 val_acc= 0.63934 time= 0.01300
Epoch: 0013 train_loss= 0.69481 train_acc= 0.52208 val_loss= 0.69380 val_acc= 0.63934 time= 0.01300
Epoch: 0014 train_loss= 0.69464 train_acc= 0.50260 val_loss= 0.69362 val_acc= 0.63934 time= 0.01400
Epoch: 0015 train_loss= 0.69446 train_acc= 0.50909 val_loss= 0.69347 val_acc= 0.63934 time= 0.01400
Epoch: 0016 train_loss= 0.69438 train_acc= 0.49610 val_loss= 0.69338 val_acc= 0.63934 time= 0.01400
Epoch: 0017 train_loss= 0.69408 train_acc= 0.51429 val_loss= 0.69322 val_acc= 0.63934 time= 0.01500
Epoch: 0018 train_loss= 0.69391 train_acc= 0.51039 val_loss= 0.69319 val_acc= 0.63934 time= 0.01300
Epoch: 0019 train_loss= 0.69386 train_acc= 0.51429 val_loss= 0.69325 val_acc= 0.63934 time= 0.01200
Epoch: 0020 train_loss= 0.69377 train_acc= 0.50909 val_loss= 0.69332 val_acc= 0.63934 time= 0.01500
Epoch: 0021 train_loss= 0.69362 train_acc= 0.51169 val_loss= 0.69332 val_acc= 0.63934 time= 0.01500
Epoch: 0022 train_loss= 0.69362 train_acc= 0.50130 val_loss= 0.69323 val_acc= 0.63934 time= 0.01400
Epoch: 0023 train_loss= 0.69354 train_acc= 0.50909 val_loss= 0.69327 val_acc= 0.63934 time= 0.01200
Epoch: 0024 train_loss= 0.69351 train_acc= 0.49610 val_loss= 0.69309 val_acc= 0.63934 time= 0.01500
Epoch: 0025 train_loss= 0.69342 train_acc= 0.51039 val_loss= 0.69287 val_acc= 0.63934 time= 0.01500
Epoch: 0026 train_loss= 0.69341 train_acc= 0.50649 val_loss= 0.69265 val_acc= 0.63934 time= 0.01500
Epoch: 0027 train_loss= 0.69335 train_acc= 0.51558 val_loss= 0.69248 val_acc= 0.63934 time= 0.01600
Epoch: 0028 train_loss= 0.69334 train_acc= 0.50779 val_loss= 0.69234 val_acc= 0.63934 time= 0.01500
Epoch: 0029 train_loss= 0.69331 train_acc= 0.50909 val_loss= 0.69238 val_acc= 0.63934 time= 0.01400
Epoch: 0030 train_loss= 0.69323 train_acc= 0.51039 val_loss= 0.69234 val_acc= 0.63934 time= 0.01300
Epoch: 0031 train_loss= 0.69326 train_acc= 0.50909 val_loss= 0.69251 val_acc= 0.63934 time= 0.01200
Epoch: 0032 train_loss= 0.69323 train_acc= 0.50779 val_loss= 0.69279 val_acc= 0.63934 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 0.69318 accuracy= 0.53279 time= 0.00600 
