Reading training examples...done
Training set properties: 25 features, 180 rankings, 15573 examples
NOTE: Adjusted stopping criterion relative to maximum loss: eps=0.987111
Iter 1: .........*(NumConst=1, SV=1, CEps=987.1111, QPEps=0.0000)
Iter 2: .........*(NumConst=2, SV=2, CEps=766.8266, QPEps=0.0001)
Iter 3: .........*(NumConst=3, SV=2, CEps=1327.5697, QPEps=0.0003)
Iter 4: .........*(NumConst=4, SV=3, CEps=1603.8404, QPEps=0.0113)
Iter 5: .........*(NumConst=5, SV=4, CEps=2507.2846, QPEps=0.0037)
Iter 6: .........*(NumConst=6, SV=5, CEps=969.9717, QPEps=0.0026)
Iter 7: .........*(NumConst=7, SV=5, CEps=286.0233, QPEps=48.5910)
Iter 8: .........*(NumConst=8, SV=5, CEps=330.1134, QPEps=47.1766)
Iter 9: .........*(NumConst=9, SV=5, CEps=206.6980, QPEps=1.0171)
Iter 10: .........*(NumConst=10, SV=6, CEps=121.9502, QPEps=48.1008)
Iter 11: .........*(NumConst=11, SV=5, CEps=197.6659, QPEps=19.2443)
Iter 12: .........*(NumConst=12, SV=5, CEps=80.2638, QPEps=33.6280)
Iter 13: .........*(NumConst=13, SV=6, CEps=79.7233, QPEps=38.3708)
Iter 14: .........*(NumConst=14, SV=5, CEps=59.3767, QPEps=4.0436)
Iter 15: .........*(NumConst=15, SV=5, CEps=93.0659, QPEps=12.9552)
Iter 16: .........*(NumConst=16, SV=5, CEps=37.9690, QPEps=17.3414)
Iter 17: .........*(NumConst=17, SV=6, CEps=38.7603, QPEps=18.3277)
Iter 18: .........*(NumConst=18, SV=6, CEps=24.9548, QPEps=10.9305)
Iter 19: .........*(NumConst=19, SV=7, CEps=31.0242, QPEps=12.3922)
Iter 20: .........*(NumConst=20, SV=5, CEps=10.5569, QPEps=4.7178)
Iter 21: .........*(NumConst=21, SV=6, CEps=14.5255, QPEps=5.2645)
Iter 22: .........*(NumConst=22, SV=6, CEps=16.1225, QPEps=5.0321)
Iter 23: .........*(NumConst=23, SV=7, CEps=9.4781, QPEps=4.6219)
Iter 24: .........*(NumConst=24, SV=7, CEps=15.1360, QPEps=3.9465)
Iter 25: .........*(NumConst=25, SV=9, CEps=9.0458, QPEps=4.4606)
Iter 26: .........*(NumConst=26, SV=10, CEps=9.1233, QPEps=4.4920)
Iter 27: .........*(NumConst=27, SV=7, CEps=5.8542, QPEps=2.9135)
Iter 28: .........*(NumConst=28, SV=8, CEps=8.2189, QPEps=2.8087)
Iter 29: .........*(NumConst=29, SV=8, CEps=4.5628, QPEps=1.9139)
Iter 30: .........*(NumConst=30, SV=9, CEps=4.0642, QPEps=2.0300)
Iter 31: .........*(NumConst=31, SV=9, CEps=5.2345, QPEps=2.0051)
Iter 32: .........*(NumConst=32, SV=8, CEps=2.5023, QPEps=1.2477)
Iter 33: .........*(NumConst=33, SV=8, CEps=2.6264, QPEps=0.9815)
Iter 34: .........*(NumConst=34, SV=8, CEps=1.7572, QPEps=0.8409)
Iter 35: .........*(NumConst=35, SV=7, CEps=1.6716, QPEps=0.8231)
Iter 36: .........*(NumConst=36, SV=7, CEps=1.2880, QPEps=0.6431)
Iter 37: .........*(NumConst=37, SV=8, CEps=1.2863, QPEps=0.6052)
Iter 38: .........(NumConst=37, SV=8, CEps=0.8934, QPEps=0.6052)
Final epsilon on KKT-Conditions: 0.89339
Upper bound on duality gap: 0.02546
Dual objective value: dval=18.35424
Primal objective value: pval=18.37971
Total number of constraints in final working set: 37 (of 37)
Number of iterations: 38
Number of calls to 'find_most_violated_constraint': 6840
Number of SV: 8 
Norm of weight vector: |w|=0.63162
Value of slack variable (on working set): xi=605.59071
Value of slack variable (global): xi=606.00780
Norm of longest difference vector: ||Psi(x,y)-Psi(x,ybar)||=9210.27617
Runtime in cpu-seconds: 0.97
Compacting linear model...done
Writing learned model...done