MLcomp version alpha Statistics: 2083 users, 670 datasets, 390 programs, 18946 runs (0 queued, 0 running), 0 workers

Run 21346

Creator	internal
Program	svmlight_multiclass-linear
Dataset	ralign-random
Task type	MulticlassClassification
Created	349d3h ago

Status: Failed!

Note: this page autoupdates while a run is in progress

Reason	(see end of log file)
Total Time
Max Memory Usage
Domain	BinaryClassification
Learn time	1h42m
Train error
Predict train time	0s
Test error
Predict test time

Log file

===== MAIN: learn based on training data =====
=== START program1: ./run learn ../dataset3/train
=== START program2: ./run learn ../program1/data
Using hyperparameter c = 0.1
Reading training examples... (1383 examples) done
Training set properties: 10 features, 2 classes
Iter 1: .........*(NumConst=1, SV=1, CEps=100.0000, QPEps=0.0000)
Iter 2: *(NumConst=2, SV=1, CEps=83.2357, QPEps=0.0000)
Iter 3: *(NumConst=3, SV=2, CEps=365.9864, QPEps=0.0001)
Iter 4: *(NumConst=4, SV=4, CEps=479.6243, QPEps=0.3446)
Iter 5: *(NumConst=5, SV=4, CEps=103.6532, QPEps=0.0465)
Iter 6: *(NumConst=6, SV=4, CEps=69.6113, QPEps=34.7634)
Iter 7: *(NumConst=7, SV=4, CEps=324.5438, QPEps=34.8039)
Iter 8: *(NumConst=8, SV=4, CEps=190.3070, QPEps=34.6704)
Iter 9: *(NumConst=9, SV=4, CEps=57.9767, QPEps=28.9408)
Iter 10: *(NumConst=10, SV=4, CEps=66.4332, QPEps=28.9408)
Iter 11: *(NumConst=11, SV=8, CEps=32.6300, QPEps=233.6055)
Iter 12: *(NumConst=12, SV=8, CEps=58.9183, QPEps=394.0196)
Iter 13: *(NumConst=13, SV=9, CEps=65.3940, QPEps=256.6399)
Iter 14: *(NumConst=14, SV=9, CEps=60.0132, QPEps=278.7661)
Iter 15: *(NumConst=15, SV=10, CEps=62.0563, QPEps=364.6411)
Iter 16: *(NumConst=16, SV=12, CEps=39.1009, QPEps=376.7713)
Iter 17: *(NumConst=17, SV=12, CEps=54.2250, QPEps=482.2600)
Iter 18: *(NumConst=18, SV=10, CEps=47.8220, QPEps=202.3117)
Iter 19: *(NumConst=19, SV=8, CEps=378.0757, QPEps=16.1162)
Iter 20: *(NumConst=20, SV=8, CEps=27.2424, QPEps=13.6135)
Iter 21: *(NumConst=21, SV=9, CEps=15.0805, QPEps=7.3467)
Iter 22: .........*(NumConst=22, SV=11, CEps=13.2209, QPEps=14.1677)
Iter 23: *(NumConst=23, SV=6, CEps=12.2997, QPEps=5.7825)
Iter 24: *(NumConst=24, SV=8, CEps=11.6259, QPEps=11.9674)
Iter 25: *(NumConst=25, SV=7, CEps=18.1094, QPEps=5.7763)
Iter 26: *(NumConst=26, SV=6, CEps=9.9905, QPEps=4.9877)
Iter 27: *(NumConst=27, SV=6, CEps=4.4880, QPEps=2.2331)
Iter 28: *(NumConst=28, SV=9, CEps=2.7102, QPEps=287.9631)
Iter 29: *(NumConst=29, SV=11, CEps=298.5025, QPEps=48.7534)
Iter 30: *(NumConst=30, SV=11, CEps=62.0389, QPEps=35.8925)
Iter 31: *(NumConst=31, SV=12, CEps=31.4632, QPEps=1.3544)
Iter 32: *(NumConst=32, SV=13, CEps=2.5016, QPEps=1.2499)
Iter 33: *(NumConst=33, SV=11, CEps=1.6885, QPEps=0.8330)
Iter 34: .........*(NumConst=34, SV=12, CEps=1.2074, QPEps=0.6027)
Iter 35: *(NumConst=35, SV=11, CEps=0.4851, QPEps=0.2425)
Iter 36: *(NumConst=36, SV=12, CEps=1.4772, QPEps=0.2424)
Iter 37: *(NumConst=37, SV=13, CEps=0.7642, QPEps=0.2424)
Iter 38: *(NumConst=38, SV=12, CEps=0.4876, QPEps=0.2068)
Iter 39: *(NumConst=39, SV=12, CEps=0.3745, QPEps=0.1868)
Iter 40: *(NumConst=40, SV=11, CEps=0.1720, QPEps=0.0856)
Iter 41: *(NumConst=41, SV=10, CEps=0.2390, QPEps=0.0856)
Iter 42: .........*(NumConst=42, SV=11, CEps=0.1114, QPEps=0.1083)
Iter 43: .........(NumConst=42, SV=11, CEps=0.0841, QPEps=0.1083)
Final epsilon on KKT-Conditions: 0.10831
Upper bound on duality gap: 0.00433
Dual objective value: dval=5.45040
Primal objective value: pval=5.45473
Total number of constraints in final working set: 42 (of 42)
Number of iterations: 43
Number of calls to 'find_most_violated_constraint': 6915
Number of SV: 11 
Norm of weight vector: |w|=0.85294
Value of slack variable (on working set): xi=50.89580
Value of slack variable (global): xi=50.90973
Norm of longest difference vector: ||Psi(x,y)-Psi(x,ybar)||=620304.07703
Runtime in cpu-seconds: 4518.40
Final number of constraints in cache: 2799
Compacting linear model...done
Writing learned model...done
=== END program2: ./run learn ../program1/data --- OK [6163s]
=== END program1: ./run learn ../dataset3/train --- OK [6163s]

===== MAIN: predict/evaluate on train data =====
=== START program4: ./run stripLabels ../dataset3/train ../program0/evalTrain.in
=== END program4: ./run stripLabels ../dataset3/train ../program0/evalTrain.in --- OK [0s]
=== START program1: ./run predict ../program0/evalTrain.in ../program0/evalTrain.out
=== START program2: ./run predict ../program0/evalTrain.in ../program0/evalTrain.out.multiclass-output
Reading model...done.
Reading test examples...
ERROR: The class label '0.000000' of example number 1 is not greater than '1'!
./run:22: Failed (RuntimeError)
=== END program2: ./run predict ../program0/evalTrain.in ../program0/evalTrain.out.multiclass-output --- FAILED [0s]
=== END program1: ./run predict ../program0/evalTrain.in ../program0/evalTrain.out --- FAILED [0s]

Run specification

• supervised-learning: Main entry for supervised learning for training and testing a program on a dataset.
  • (learner:Program) binary-to-multi: Allows multiclass classification to be run on binary classification datasets (trivial reduction).
    • (multiclassLearner:Program[MulticlassClassification]) svmlight_multiclass-linear: SVMlight for multiclass classification (http://svmlight.joachims.org/svm_multiclass.html)
  • (dataset:Dataset) ralign-random: an alignment problem with balanced classes
  • (stripper:Program[Strip]) binary-utils: Validates and inspects a dataset in BinaryClassification format.
  • (evaluator:Program[Evaluate]) classification-evaluator: Evaluates predictions of classification datasets (discrete outputs).

Results

• doTrain:
  • predict:
    • predict:
      • success: false
      • time: 0
    • success: false
    • time: 0
  • strip:
    • success: true
    • time: 0
• exitCode: 0
• learn:
  • learn:
    • success: true
    • time: 6163
  • success: true
  • time: 6163
• success: false

Comments: