Num weight bits = 18
learning rate = 10
initial_t = 1
power_t = 0.5
decay_learning_rate = 1
creating cache_file = train-sets/multiclass.cache
Reading datafile = train-sets/multiclass
num sources = 1
average    since         example     example  current  current  current
loss       last          counter      weight    label  predict features
0.000000   0.000000          1      1.0          1        1        2
0.500000   1.000000          2      2.0          2        1        2
0.750000   1.000000          4      4.0          4        3        2
0.875000   1.000000          8      8.0          8        7        2
0.687500   0.500000         16     16.0          6        6        2
0.343750   0.000000         32     32.0          2        2        2
0.171875   0.000000         64     64.0          4        4        2

finished run
number of examples per pass = 10
passes used = 10
weighted example sum = 100
weighted label sum = 0
average loss = 0.11
best constant = -0.010101
total feature number = 200