Num weight bits = 18
learning rate = 0.5
initial_t = 0
power_t = 0.5
decay_learning_rate = 1
creating cache_file = train-sets/0001.dat.cache
Reading datafile = train-sets/0001.dat
num sources = 1
average    since         example     example  current  current  current
loss       last          counter      weight    label  predict features
1.000000   1.000000            1         1.0   1.0000   0.0000       51
0.513618   0.027236            2         2.0   0.0000   0.1650      104
0.263121   0.012624            4         4.0   0.0000   0.0569      135
0.237739   0.212356            8         8.0   0.0000   0.2024      146
0.248570   0.259401           16        16.0   1.0000   0.2048      143
0.230779   0.212988           32        32.0   1.0000   0.4685       70
0.232955   0.235132           64        64.0   0.0000   0.4225       34
0.219769   0.206582          128       128.0   0.0000   0.1011       30
0.164101   0.164101          256       256.0   0.0000   0.1328       72 h

finished run
number of examples per pass = 180
passes used = 2
weighted example sum = 360
weighted label sum = 160
average loss = 0.152951 h
best constant = 0.444444
best constant's loss = 0.246914
total feature number = 27566