Reading training examples...done
Training set properties: 23 features, 90 rankings, 8163 examples
NOTE: Adjusted stopping criterion relative to maximum loss: eps=0.527100
Iter 1: .........*(NumConst=1, SV=1, CEps=527.1000, QPEps=0.0000)
Iter 2: .........*(NumConst=2, SV=2, CEps=491.1077, QPEps=0.0001)
Iter 3: .........*(NumConst=3, SV=3, CEps=823.0801, QPEps=0.0021)
Iter 4: .........*(NumConst=4, SV=3, CEps=2415.3230, QPEps=0.0023)
Iter 5: .........*(NumConst=5, SV=4, CEps=1252.8644, QPEps=0.0023)
Iter 6: .........*(NumConst=6, SV=6, CEps=1027.1513, QPEps=45.0312)
Iter 7: .........*(NumConst=7, SV=5, CEps=211.6927, QPEps=49.0010)
Iter 8: .........*(NumConst=8, SV=6, CEps=213.1187, QPEps=49.3422)
Iter 9: .........*(NumConst=9, SV=8, CEps=198.4228, QPEps=49.8647)
Iter 10: .........*(NumConst=10, SV=6, CEps=119.1121, QPEps=0.0001)
Iter 11: .........*(NumConst=11, SV=6, CEps=80.7875, QPEps=4.3758)
Iter 12: .........*(NumConst=12, SV=6, CEps=91.5068, QPEps=18.0272)
Iter 13: .........*(NumConst=13, SV=7, CEps=63.5184, QPEps=31.4285)
Iter 14: .........*(NumConst=14, SV=7, CEps=42.3524, QPEps=1.3885)
Iter 15: .........*(NumConst=15, SV=7, CEps=82.1394, QPEps=13.1772)
Iter 16: .........*(NumConst=16, SV=6, CEps=24.8905, QPEps=0.0000)
Iter 17: .........*(NumConst=17, SV=6, CEps=37.0693, QPEps=0.0000)
Iter 18: .........*(NumConst=18, SV=6, CEps=44.5610, QPEps=0.0000)
Iter 19: .........*(NumConst=19, SV=6, CEps=16.3966, QPEps=0.0000)
Iter 20: .........*(NumConst=20, SV=6, CEps=16.9851, QPEps=7.1410)
Iter 21: .........*(NumConst=21, SV=6, CEps=13.3690, QPEps=0.0000)
Iter 22: .........*(NumConst=22, SV=6, CEps=7.4083, QPEps=0.0000)
Iter 23: .........*(NumConst=23, SV=7, CEps=5.6581, QPEps=1.9688)
Iter 24: .........*(NumConst=24, SV=6, CEps=11.6596, QPEps=1.9434)
Iter 25: .........*(NumConst=25, SV=6, CEps=6.4643, QPEps=0.0000)
Iter 26: .........*(NumConst=26, SV=8, CEps=4.3890, QPEps=2.1151)
Iter 27: .........*(NumConst=27, SV=6, CEps=4.5695, QPEps=0.0000)
Iter 28: .........*(NumConst=28, SV=6, CEps=2.8640, QPEps=0.0000)
Iter 29: .........*(NumConst=29, SV=5, CEps=2.9885, QPEps=0.0000)
Iter 30: .........*(NumConst=30, SV=7, CEps=1.8844, QPEps=0.0000)
Iter 31: .........*(NumConst=31, SV=7, CEps=5.2939, QPEps=0.0000)
Iter 32: .........*(NumConst=32, SV=6, CEps=1.7061, QPEps=0.0000)
Iter 33: .........*(NumConst=33, SV=6, CEps=1.7233, QPEps=0.0000)
Iter 34: .........*(NumConst=34, SV=7, CEps=1.0297, QPEps=0.2222)
Iter 35: .........*(NumConst=35, SV=6, CEps=0.8631, QPEps=0.0000)
Iter 36: .........*(NumConst=36, SV=6, CEps=1.8529, QPEps=0.0695)
Iter 37: .........*(NumConst=37, SV=7, CEps=1.0558, QPEps=0.1155)
Iter 38: .........*(NumConst=38, SV=7, CEps=1.1179, QPEps=0.3964)
Iter 39: .........*(NumConst=39, SV=6, CEps=0.6449, QPEps=0.1100)
Iter 40: .........(NumConst=39, SV=6, CEps=0.4213, QPEps=0.1100)
Final epsilon on KKT-Conditions: 0.42129
Upper bound on duality gap: 0.02093
Dual objective value: dval=16.02654
Primal objective value: pval=16.04747
Total number of constraints in final working set: 39 (of 39)
Number of iterations: 40
Number of calls to 'find_most_violated_constraint': 3600
Number of SV: 6 
Norm of weight vector: |w|=1.32043
Value of slack variable (on working set): xi=303.20274
Value of slack variable (global): xi=303.51401
Norm of longest difference vector: ||Psi(x,y)-Psi(x,ybar)||=3465.23275
Runtime in cpu-seconds: 0.28
Compacting linear model...done
Writing learned model...done