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
0.508353   0.016707            2         2.0   0.0000   0.1293      104
0.260650   0.012946            4         4.0   0.0000   0.0607      135
0.242874   0.225099            8         8.0   0.0000   0.2086      146
0.252709   0.262543           16        16.0   1.0000   0.2181      143
0.232971   0.213234           32        32.0   1.0000   0.4298       70
0.233056   0.233140           64        64.0   0.0000   0.3871       34
0.219917   0.206779          128       128.0   0.0000   0.1824       30
0.171716   0.171716          256       256.0   0.0000   0.1204       72 h

finished run
number of examples per pass = 180
passes used = 2
weighted example sum = 360
weighted label sum = 160
average loss = 0.14944 h
best constant = 0.444444
best constant's loss = 0.246914
total feature number = 27566