Epoch: 0001 train_loss= 2.07786 train_acc= 0.16226 val_loss= 2.07602 val_acc= 0.17241 time= 0.50712
Epoch: 0002 train_loss= 2.07356 train_acc= 0.14340 val_loss= 2.07830 val_acc= 0.17241 time= 0.00500
Epoch: 0003 train_loss= 2.07061 train_acc= 0.17358 val_loss= 2.08018 val_acc= 0.17241 time= 0.00500
Epoch: 0004 train_loss= 2.07031 train_acc= 0.16226 val_loss= 2.08234 val_acc= 0.17241 time= 0.00107
Epoch: 0005 train_loss= 2.06812 train_acc= 0.16604 val_loss= 2.08396 val_acc= 0.17241 time= 0.00000
Epoch: 0006 train_loss= 2.06574 train_acc= 0.16226 val_loss= 2.08513 val_acc= 0.17241 time= 0.00000
Epoch: 0007 train_loss= 2.06428 train_acc= 0.16226 val_loss= 2.08582 val_acc= 0.17241 time= 0.01563
Epoch: 0008 train_loss= 2.06300 train_acc= 0.16604 val_loss= 2.08590 val_acc= 0.17241 time= 0.00000
Epoch: 0009 train_loss= 2.06079 train_acc= 0.16226 val_loss= 2.08549 val_acc= 0.17241 time= 0.00000
Epoch: 0010 train_loss= 2.06184 train_acc= 0.15849 val_loss= 2.08460 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.05879 train_acc= 0.15849 val_loss= 2.08363 val_acc= 0.17241 time= 0.00000
Epoch: 0012 train_loss= 2.05768 train_acc= 0.16604 val_loss= 2.08225 val_acc= 0.17241 time= 0.00000
Epoch: 0013 train_loss= 2.05716 train_acc= 0.16604 val_loss= 2.08066 val_acc= 0.17241 time= 0.01563
Epoch: 0014 train_loss= 2.06077 train_acc= 0.16604 val_loss= 2.07932 val_acc= 0.17241 time= 0.00000
Epoch: 0015 train_loss= 2.05816 train_acc= 0.16604 val_loss= 2.07832 val_acc= 0.17241 time= 0.00000
Epoch: 0016 train_loss= 2.05672 train_acc= 0.16981 val_loss= 2.07733 val_acc= 0.17241 time= 0.00000
Epoch: 0017 train_loss= 2.05502 train_acc= 0.16981 val_loss= 2.07652 val_acc= 0.17241 time= 0.01563
Epoch: 0018 train_loss= 2.05741 train_acc= 0.15849 val_loss= 2.07603 val_acc= 0.17241 time= 0.00000
Epoch: 0019 train_loss= 2.05372 train_acc= 0.15849 val_loss= 2.07544 val_acc= 0.17241 time= 0.00000
Epoch: 0020 train_loss= 2.05741 train_acc= 0.15472 val_loss= 2.07491 val_acc= 0.17241 time= 0.01563
Epoch: 0021 train_loss= 2.05539 train_acc= 0.16604 val_loss= 2.07439 val_acc= 0.17241 time= 0.00000
Epoch: 0022 train_loss= 2.05443 train_acc= 0.18868 val_loss= 2.07432 val_acc= 0.03448 time= 0.00000
Epoch: 0023 train_loss= 2.05798 train_acc= 0.15472 val_loss= 2.07430 val_acc= 0.03448 time= 0.01563
Epoch: 0024 train_loss= 2.05586 train_acc= 0.18491 val_loss= 2.07433 val_acc= 0.03448 time= 0.00000
Epoch: 0025 train_loss= 2.05525 train_acc= 0.15094 val_loss= 2.07449 val_acc= 0.03448 time= 0.00000
Epoch: 0026 train_loss= 2.05614 train_acc= 0.15472 val_loss= 2.07440 val_acc= 0.03448 time= 0.01562
Epoch: 0027 train_loss= 2.05733 train_acc= 0.16226 val_loss= 2.07418 val_acc= 0.03448 time= 0.00000
Epoch: 0028 train_loss= 2.05442 train_acc= 0.15472 val_loss= 2.07420 val_acc= 0.03448 time= 0.00000
Epoch: 0029 train_loss= 2.05578 train_acc= 0.15094 val_loss= 2.07377 val_acc= 0.03448 time= 0.01563
Epoch: 0030 train_loss= 2.05644 train_acc= 0.15094 val_loss= 2.07328 val_acc= 0.03448 time= 0.00000
Epoch: 0031 train_loss= 2.05467 train_acc= 0.15849 val_loss= 2.07293 val_acc= 0.03448 time= 0.00000
Epoch: 0032 train_loss= 2.05440 train_acc= 0.14340 val_loss= 2.07276 val_acc= 0.03448 time= 0.01563
Epoch: 0033 train_loss= 2.05568 train_acc= 0.14717 val_loss= 2.07300 val_acc= 0.03448 time= 0.00000
Epoch: 0034 train_loss= 2.05370 train_acc= 0.15094 val_loss= 2.07332 val_acc= 0.03448 time= 0.00000
Epoch: 0035 train_loss= 2.05490 train_acc= 0.13585 val_loss= 2.07377 val_acc= 0.03448 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.08003 accuracy= 0.08475 time= 0.01563 
