your learning rate is too high, setting it to 1
Num weight bits = 13
learning rate = 1
initial_t = 1
power_t = 0.5
using no cache
Reading datafile = train-sets/wiki1K.dat
num sources = 1
average    since         example     example  current  current  current
loss       last          counter      weight    label  predict features
10.380830  10.380830           3         3.0  unknown   0.0000       37
10.456700  10.532571           6         6.0  unknown   0.0000       13
10.398070  10.327713          11        11.0  unknown   0.0000       31
10.499986  10.601903          22        22.0  unknown   0.0000        1
10.451025  10.402064          44        44.0  unknown   0.0000      165
10.446713  10.442300          87        87.0  unknown   0.0000       28
10.076803  9.706893          174       174.0  unknown   0.0000       16
9.506702   8.936600          348       348.0  unknown   0.0000        1
8.930677   8.354652          696       696.0  unknown   0.0000      142

finished run
number of examples = 1000
weighted example sum = 1000
weighted label sum = 0
average loss = 8.716
best constant = 1
total feature number = 86919