Reading training examples...done
Training set properties: 25 features, 180 rankings, 15555 examples
NOTE: Adjusted stopping criterion relative to maximum loss: eps=1.003494
Iter 1: .........*(NumConst=1, SV=1, CEps=1003.4944, QPEps=0.0000)
Iter 2: .........*(NumConst=2, SV=2, CEps=800.0460, QPEps=0.0003)
Iter 3: .........*(NumConst=3, SV=2, CEps=1367.1094, QPEps=0.0005)
Iter 4: .........*(NumConst=4, SV=3, CEps=1634.2467, QPEps=0.0039)
Iter 5: .........*(NumConst=5, SV=4, CEps=2477.9991, QPEps=0.0063)
Iter 6: .........*(NumConst=6, SV=5, CEps=1249.0319, QPEps=0.0013)
Iter 7: .........*(NumConst=7, SV=5, CEps=298.7508, QPEps=2.7867)
Iter 8: .........*(NumConst=8, SV=6, CEps=400.1190, QPEps=48.6528)
Iter 9: .........*(NumConst=9, SV=6, CEps=205.4474, QPEps=41.3010)
Iter 10: .........*(NumConst=10, SV=6, CEps=139.2540, QPEps=49.8288)
Iter 11: .........*(NumConst=11, SV=6, CEps=250.6164, QPEps=48.9460)
Iter 12: .........*(NumConst=12, SV=6, CEps=156.6573, QPEps=48.2654)
Iter 13: .........*(NumConst=13, SV=7, CEps=75.8217, QPEps=37.1472)
Iter 14: .........*(NumConst=14, SV=7, CEps=64.3755, QPEps=31.0703)
Iter 15: .........*(NumConst=15, SV=7, CEps=54.7764, QPEps=27.1290)
Iter 16: .........*(NumConst=16, SV=7, CEps=51.7763, QPEps=24.7614)
Iter 17: .........*(NumConst=17, SV=7, CEps=37.2624, QPEps=16.9257)
Iter 18: .........*(NumConst=18, SV=8, CEps=27.4575, QPEps=13.1518)
Iter 19: .........*(NumConst=19, SV=8, CEps=21.7821, QPEps=1.1087)
Iter 20: .........*(NumConst=20, SV=8, CEps=31.7357, QPEps=9.2783)
Iter 21: .........*(NumConst=21, SV=8, CEps=20.4163, QPEps=1.3768)
Iter 22: .........*(NumConst=22, SV=8, CEps=15.4778, QPEps=7.3150)
Iter 23: .........*(NumConst=23, SV=9, CEps=12.9698, QPEps=6.3807)
Iter 24: .........*(NumConst=24, SV=10, CEps=11.9863, QPEps=4.4697)
Iter 25: .........*(NumConst=25, SV=11, CEps=13.6246, QPEps=5.5604)
Iter 26: .........*(NumConst=26, SV=12, CEps=8.9522, QPEps=4.4411)
Iter 27: .........*(NumConst=27, SV=12, CEps=7.1055, QPEps=3.4597)
Iter 28: .........*(NumConst=28, SV=10, CEps=4.8791, QPEps=2.1330)
Iter 29: .........*(NumConst=29, SV=11, CEps=7.1251, QPEps=2.3538)
Iter 30: .........*(NumConst=30, SV=12, CEps=4.4074, QPEps=1.9947)
Iter 31: .........*(NumConst=31, SV=12, CEps=3.3332, QPEps=1.6285)
Iter 32: .........*(NumConst=32, SV=12, CEps=3.5255, QPEps=1.2707)
Iter 33: .........*(NumConst=33, SV=12, CEps=2.7243, QPEps=1.2916)
Iter 34: .........*(NumConst=34, SV=12, CEps=1.1659, QPEps=0.5557)
Iter 35: .........*(NumConst=35, SV=12, CEps=1.1860, QPEps=0.5741)
Iter 36: .........*(NumConst=36, SV=13, CEps=1.2170, QPEps=0.5806)
Iter 37: .........*(NumConst=37, SV=11, CEps=1.6530, QPEps=0.5127)
Iter 38: .........*(NumConst=38, SV=13, CEps=1.0299, QPEps=0.4833)
Iter 39: .........(NumConst=38, SV=13, CEps=0.7268, QPEps=0.4833)
Final epsilon on KKT-Conditions: 0.72678
Upper bound on duality gap: 0.02437
Dual objective value: dval=18.79417
Primal objective value: pval=18.81854
Total number of constraints in final working set: 38 (of 38)
Number of iterations: 39
Number of calls to 'find_most_violated_constraint': 7020
Number of SV: 13 
Norm of weight vector: |w|=0.65949
Value of slack variable (on working set): xi=619.57080
Value of slack variable (global): xi=620.03601
Norm of longest difference vector: ||Psi(x,y)-Psi(x,ybar)||=8606.58016
Runtime in cpu-seconds: 0.88
Compacting linear model...done
Writing learned model...done