deit ouput

Cost at epoch 0 is 4.611058227040551
Cost at epoch 1 is 0.9889081553979353
test set accuracy
Checking accuracy
scores: tensor([[ 33.9686,  33.2787, -31.1509,  ..., -25.5279, -36.7728, -24.9331],
        [ 33.9695,  33.2792, -31.1509,  ..., -25.5264, -36.7719, -24.9356],
        [ 33.9690,  33.2784, -31.1496,  ..., -25.5270, -36.7717, -24.9326],
        ...,
        [ 33.9692,  33.2780, -31.1487,  ..., -25.5267, -36.7713, -24.9314],
        [ 33.9654,  33.2793, -31.1575,  ..., -25.5372, -36.7818, -24.9307],
        [ 33.9687,  33.2778, -31.1490,  ..., -25.5278, -36.7719, -24.9300]],
       device='cuda:0')
predictions: tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0, 0, 0, 0, 0, 0, 0], device='cuda:0')
y: tensor([1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0,
        1, 1, 0, 1, 0, 1, 1, 1], device='cuda:0')

###  many more prints later
predictions: tensor([0, 0, 0, 0, 0, 0], device='cuda:0')
y: tensor([0, 1, 1, 0, 1, 1], device='cuda:0')
Got 80 / 198 with accuracy 40.40
Precision: 0.1632
Recall: 0.4040
F1-Score: 0.2325