Num weight bits = 18
learning rate = 10
initial_t = 1
power_t = 0.5
decay_learning_rate = 1
creating cache_file = train-sets/seq_small.cache
Reading from train-sets/seq_small
num sources = 1
average    since      sequence         example            current label      current predicted  current   cur   cur         predic.        examples
loss       last        counter          weight          sequence prefix        sequence prefix features  pass   pol            made          gener.
0.666667   0.666667          1        6.000000   [ 1  3  2  1  4  3   ] [ 1  1  1  1  1  1   ]       12     0     0               6               0
0.333333   0.000000          2       12.000000   [ 1  3  2  1  4  3   ] [ 1  3  2  1  4  3   ]       12     1     0              12               6
0.222222   0.000000          3       18.000000   [ 1  3  2  1  4  3   ] [ 1  3  2  1  4  3   ]       12     2     0              18              12
0.166667   0.000000          4       24.000000   [ 1  3  2  1  4  3   ] [ 1  3  2  1  4  3   ]       12     3     0              24              18
0.083333   0.000000          8       48.000000   [ 1  3  2  1  4  3   ] [ 1  3  2  1  4  3   ]       12     7     1              51              42

finished run
number of examples = 12
weighted example sum = 72
weighted label sum = 0
average loss = 0.05556
best constant = -0.01408
total feature number = 144