Reading training examples...done
Training set properties: 23 features, 90 rankings, 8146 examples
NOTE: Adjusted stopping criterion relative to maximum loss: eps=0.497278
Iter 1: .........*(NumConst=1, SV=1, CEps=497.2778, QPEps=0.0000)
Iter 2: .........*(NumConst=2, SV=2, CEps=443.3905, QPEps=0.0001)
Iter 3: .........*(NumConst=3, SV=3, CEps=898.1626, QPEps=0.0011)
Iter 4: .........*(NumConst=4, SV=3, CEps=2549.5678, QPEps=0.0001)
Iter 5: .........*(NumConst=5, SV=5, CEps=1421.8780, QPEps=0.0013)
Iter 6: .........*(NumConst=6, SV=5, CEps=308.2655, QPEps=0.0014)
Iter 7: .........*(NumConst=7, SV=5, CEps=200.6500, QPEps=37.1622)
Iter 8: .........*(NumConst=8, SV=6, CEps=138.5492, QPEps=49.3634)
Iter 9: .........*(NumConst=9, SV=7, CEps=166.5072, QPEps=49.3623)
Iter 10: .........*(NumConst=10, SV=6, CEps=121.0655, QPEps=0.0001)
Iter 11: .........*(NumConst=11, SV=6, CEps=55.8528, QPEps=0.0002)
Iter 12: .........*(NumConst=12, SV=5, CEps=54.1312, QPEps=0.0000)
Iter 13: .........*(NumConst=13, SV=6, CEps=61.9247, QPEps=13.5129)
Iter 14: .........*(NumConst=14, SV=6, CEps=56.6925, QPEps=0.0000)
Iter 15: .........*(NumConst=15, SV=6, CEps=46.0722, QPEps=8.8946)
Iter 16: .........*(NumConst=16, SV=7, CEps=28.1302, QPEps=6.5921)
Iter 17: .........*(NumConst=17, SV=7, CEps=16.1046, QPEps=6.5797)
Iter 18: .........*(NumConst=18, SV=6, CEps=22.1459, QPEps=0.0000)
Iter 19: .........*(NumConst=19, SV=7, CEps=13.4654, QPEps=6.0357)
Iter 20: .........*(NumConst=20, SV=6, CEps=17.2160, QPEps=0.0000)
Iter 21: .........*(NumConst=21, SV=6, CEps=10.0082, QPEps=0.0000)
Iter 22: .........*(NumConst=22, SV=6, CEps=8.4213, QPEps=0.0000)
Iter 23: .........*(NumConst=23, SV=6, CEps=8.2652, QPEps=0.0000)
Iter 24: .........*(NumConst=24, SV=6, CEps=4.7833, QPEps=0.0000)
Iter 25: .........*(NumConst=25, SV=6, CEps=3.9023, QPEps=0.3472)
Iter 26: .........*(NumConst=26, SV=7, CEps=3.8472, QPEps=1.2844)
Iter 27: .........*(NumConst=27, SV=6, CEps=3.5925, QPEps=1.6184)
Iter 28: .........*(NumConst=28, SV=6, CEps=1.6443, QPEps=0.0000)
Iter 29: .........*(NumConst=29, SV=6, CEps=3.6883, QPEps=0.1894)
Iter 30: .........*(NumConst=30, SV=6, CEps=1.4306, QPEps=0.2214)
Iter 31: .........*(NumConst=31, SV=6, CEps=2.1601, QPEps=0.4210)
Iter 32: .........*(NumConst=32, SV=6, CEps=1.6431, QPEps=0.0000)
Iter 33: .........*(NumConst=33, SV=6, CEps=1.6729, QPEps=0.3778)
Iter 34: .........*(NumConst=34, SV=5, CEps=0.7349, QPEps=0.0000)
Iter 35: .........*(NumConst=35, SV=5, CEps=1.1561, QPEps=0.3271)
Iter 36: .........*(NumConst=36, SV=6, CEps=1.3423, QPEps=0.1106)
Iter 37: .........*(NumConst=37, SV=6, CEps=0.7529, QPEps=0.1604)
Iter 38: .........(NumConst=37, SV=6, CEps=0.4812, QPEps=0.1604)
Final epsilon on KKT-Conditions: 0.48116
Upper bound on duality gap: 0.02436
Dual objective value: dval=15.09473
Primal objective value: pval=15.11908
Total number of constraints in final working set: 37 (of 37)
Number of iterations: 38
Number of calls to 'find_most_violated_constraint': 3420
Number of SV: 6 
Norm of weight vector: |w|=1.19521
Value of slack variable (on working set): xi=287.61519
Value of slack variable (global): xi=288.09633
Norm of longest difference vector: ||Psi(x,y)-Psi(x,ybar)||=3517.12555
Runtime in cpu-seconds: 0.30
Compacting linear model...done
Writing learned model...done