Num weight bits = 18
learning rate = 0.5
initial_t = 0
power_t = 0.5
using no cache
Reading datafile = train-sets/0001.dat
num sources = 1
average    since         example     example  current  current  current
loss       last          counter      weight    label  predict features
0.626139   0.626139            1         1.0   1.0000   0.2087       51
0.593221   0.560302            2         2.0   0.0000   0.7485      104
0.415928   0.238635            4         4.0   0.0000   0.4452      135
0.315393   0.214858            8         8.0   0.0000   0.3680      146
0.277266   0.239140           16        16.0   1.0000   0.3655       24
0.257687   0.238107           32        32.0   0.0000   0.3811       32
0.247343   0.237000           64        64.0   0.0000   0.3351       61
0.246230   0.245117          128       128.0   1.0000   0.5023      106

finished run
number of examples per pass = 200
passes used = 1
weighted example sum = 200
weighted label sum = 91
average loss = 0.238693
best constant = 0.455
best constant's loss = 0.247975
total feature number = 15482