using l1 regularization = 0.01
Num weight bits = 18
learning rate = 0.5
initial_t = 0
power_t = 0.5
final_regressor = models/mask.model
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
1.000000   1.000000            1         1.0   1.0000   0.0000       51
0.513258   0.026516            2         2.0   0.0000   0.1628      104
0.262827   0.012396            4         4.0   0.0000   0.0559      135
0.237630   0.212433            8         8.0   0.0000   0.2043      146
0.243325   0.249019           16        16.0   1.0000   0.3164       24
0.237450   0.231576           32        32.0   0.0000   0.2108       32
0.233099   0.228747           64        64.0   0.0000   0.2045       61
0.233283   0.233467          128       128.0   1.0000   0.4665      106

finished run
number of examples per pass = 200
passes used = 1
weighted example sum = 200
weighted label sum = 91
average loss = 0.224127
best constant = 0.455
best constant's loss = 0.247975
total feature number = 15482