ULR Fold 2

Back to ULR overview · Back to main index

Fold metrics

MetricValue
Test accuracy53.43%
Test F1 score0.5624
Hierarchical loss0.90723142
P-adic loss (total)397.09641926
P-adic loss (mean)0.25937062
Prime base79
Number of tags (input features)5,904
Non-zero parameters4,447 / 3,253,655 (99.9% sparse)
L1 regularization (C)1.0000
Training samples6,159
Test samples1,531

P-adic loss breakdown

AgreementCountShareCost per mistakeTotal contribution
Exact match81853.43%0.0000000.000000
p^630.20%0.0000000.000000
p^570.46%0.0000000.000000
p^4362.35%0.0000000.000001
p^3593.85%0.0000020.000120
p^21278.30%0.0001600.020349
p^1855.55%0.0126581.075949
p^039625.87%1.000000396.000000

About L1 regularization

L1 (Lasso) regularization promotes sparsity by driving many coefficients to exactly zero. This model uses ALL available tags (5,904) but L1 regularization selects which features are actually used. The number of non-zero parameters (4,447) indicates how many coefficients the model actually uses.