Epoch: 0001 train_loss= 0.70104 train_acc= 0.51273 val_loss= 0.69792 val_acc= 0.51613 time= 0.28127
Epoch: 0002 train_loss= 0.69798 train_acc= 0.51818 val_loss= 0.69571 val_acc= 0.51613 time= 0.01563
Epoch: 0003 train_loss= 0.69575 train_acc= 0.51818 val_loss= 0.69422 val_acc= 0.51613 time= 0.01563
Epoch: 0004 train_loss= 0.69428 train_acc= 0.51818 val_loss= 0.69328 val_acc= 0.51613 time= 0.01563
Epoch: 0005 train_loss= 0.69317 train_acc= 0.51636 val_loss= 0.69279 val_acc= 0.51613 time= 0.00000
Epoch: 0006 train_loss= 0.69256 train_acc= 0.51636 val_loss= 0.69261 val_acc= 0.51613 time= 0.01563
Epoch: 0007 train_loss= 0.69230 train_acc= 0.51636 val_loss= 0.69261 val_acc= 0.51613 time= 0.01563
Epoch: 0008 train_loss= 0.69256 train_acc= 0.51818 val_loss= 0.69268 val_acc= 0.51613 time= 0.00000
Epoch: 0009 train_loss= 0.69232 train_acc= 0.52000 val_loss= 0.69277 val_acc= 0.51613 time= 0.01563
Epoch: 0010 train_loss= 0.69224 train_acc= 0.52000 val_loss= 0.69284 val_acc= 0.51613 time= 0.01563
Epoch: 0011 train_loss= 0.69255 train_acc= 0.52545 val_loss= 0.69287 val_acc= 0.51613 time= 0.01563
Epoch: 0012 train_loss= 0.69229 train_acc= 0.52545 val_loss= 0.69283 val_acc= 0.51613 time= 0.00000
Epoch: 0013 train_loss= 0.69251 train_acc= 0.52727 val_loss= 0.69274 val_acc= 0.51613 time= 0.01563
Epoch: 0014 train_loss= 0.69198 train_acc= 0.52727 val_loss= 0.69262 val_acc= 0.51613 time= 0.01563
Epoch: 0015 train_loss= 0.69165 train_acc= 0.53273 val_loss= 0.69248 val_acc= 0.51613 time= 0.00000
Epoch: 0016 train_loss= 0.69103 train_acc= 0.52545 val_loss= 0.69235 val_acc= 0.51613 time= 0.01563
Epoch: 0017 train_loss= 0.69110 train_acc= 0.54182 val_loss= 0.69221 val_acc= 0.51613 time= 0.01563
Epoch: 0018 train_loss= 0.69064 train_acc= 0.53091 val_loss= 0.69207 val_acc= 0.51613 time= 0.01563
Epoch: 0019 train_loss= 0.69058 train_acc= 0.54000 val_loss= 0.69195 val_acc= 0.53226 time= 0.00000
Epoch: 0020 train_loss= 0.69076 train_acc= 0.53636 val_loss= 0.69186 val_acc= 0.53226 time= 0.01563
Epoch: 0021 train_loss= 0.69031 train_acc= 0.54545 val_loss= 0.69181 val_acc= 0.53226 time= 0.01563
Epoch: 0022 train_loss= 0.69058 train_acc= 0.52909 val_loss= 0.69176 val_acc= 0.53226 time= 0.00000
Epoch: 0023 train_loss= 0.68996 train_acc= 0.55636 val_loss= 0.69171 val_acc= 0.53226 time= 0.01563
Epoch: 0024 train_loss= 0.68972 train_acc= 0.55455 val_loss= 0.69164 val_acc= 0.53226 time= 0.01562
Epoch: 0025 train_loss= 0.68994 train_acc= 0.54545 val_loss= 0.69159 val_acc= 0.54839 time= 0.01562
Epoch: 0026 train_loss= 0.68923 train_acc= 0.57091 val_loss= 0.69155 val_acc= 0.53226 time= 0.00000
Epoch: 0027 train_loss= 0.68997 train_acc= 0.53818 val_loss= 0.69150 val_acc= 0.53226 time= 0.01563
Epoch: 0028 train_loss= 0.68885 train_acc= 0.55091 val_loss= 0.69139 val_acc= 0.54839 time= 0.01563
Epoch: 0029 train_loss= 0.68941 train_acc= 0.55273 val_loss= 0.69135 val_acc= 0.58065 time= 0.00000
Epoch: 0030 train_loss= 0.68917 train_acc= 0.57455 val_loss= 0.69130 val_acc= 0.62903 time= 0.01563
Epoch: 0031 train_loss= 0.68998 train_acc= 0.61818 val_loss= 0.69116 val_acc= 0.58065 time= 0.01563
Epoch: 0032 train_loss= 0.68800 train_acc= 0.58182 val_loss= 0.69118 val_acc= 0.54839 time= 0.01563
Epoch: 0033 train_loss= 0.68867 train_acc= 0.54000 val_loss= 0.69116 val_acc= 0.54839 time= 0.00000
Epoch: 0034 train_loss= 0.68811 train_acc= 0.54727 val_loss= 0.69101 val_acc= 0.56452 time= 0.01563
Epoch: 0035 train_loss= 0.68939 train_acc= 0.55455 val_loss= 0.69084 val_acc= 0.56452 time= 0.01563
Epoch: 0036 train_loss= 0.68917 train_acc= 0.54000 val_loss= 0.69094 val_acc= 0.61290 time= 0.00000
Epoch: 0037 train_loss= 0.68767 train_acc= 0.60909 val_loss= 0.69123 val_acc= 0.61290 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.68867 accuracy= 0.63710 time= 0.00000 
