blob: e5c59fef2557d81395f48bb5e7cff4e569eaad01 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
|
using l2 regularization = 1
enabling BFGS based optimization **without** curvature calculation
Num weight bits = 20
learning rate = 0.5
initial_t = 0
power_t = 0.5
decay_learning_rate = 1
m = 7
Allocated 72M for weights and mem
## avg. loss der. mag. d. m. cond. wolfe1 wolfe2 mix fraction curvature dir. magnitude step size
creating cache_file = train-sets/rcv1_small.dat.cache
Reading datafile = train-sets/rcv1_small.dat
num sources = 1
1 0.69315 0.00266 0.39836 0.48297 156.06891 0.82481
3 0.52081 0.00612 0.13742 0.524507 0.091092 42.96110 1.00000
4 0.48999 0.00251 0.04577 0.286251 -0.382286 2.38434 1.00000
5 0.47993 0.00007 0.00448 0.617627 0.225808 0.71197 1.00000
6 0.47794 0.00001 0.00174 0.691628 0.377800 0.93214 1.00000
7 0.47685 0.00001 0.00041 0.606087 0.209707 0.18141 1.00000
8 0.47668 0.00000 0.00001 0.538842 0.077584 0.00292 1.00000
finished run
number of examples = 8000
weighted example sum = 8000
weighted label sum = -656
average loss = 0.461878
best constant = -0.164369
best constant's loss = 0.689781
total feature number = 629912
|