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
0.000000   0.000000            1         1.0   1.0000   1.0000       51
0.191594   0.383189            2         2.0   0.0000   0.6190      104
0.095797   0.000000            4         4.0   0.0000   0.0000      135
0.091403   0.087008            8         8.0   0.0000   0.0000      146
0.075218   0.059034           16        16.0   1.0000   1.0000       24
0.063804   0.052389           32        32.0   0.0000   0.0000       32
0.081903   0.100002           64        64.0   0.0000   0.0000       61
0.081818   0.081734          128       128.0   1.0000   1.0000      106

finished run
number of examples per pass = 200
passes used = 1
weighted example sum = 200
weighted label sum = 91
average loss = 0.0706819
best constant = 0.455
best constant's loss = 0.247975
total feature number = 15482