PCLR Fold 2

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	5.92%
Test F1 score	0.0577
Hierarchical loss	0.76321967
P-adic loss (total)	2097.85534623
P-adic loss (mean)	0.77640834
Prime base	79
Training samples	10,857
Test samples	2,702
Trained at	2026-05-25T05:31:39+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	160	5.92%	0.000000	0.000000
p^4	4	0.15%	0.000000	0.000000
p^3	96	3.55%	0.000002	0.000195
p^2	202	7.48%	0.000160	0.032367
p^1	144	5.33%	0.012658	1.822785
p^0	2,096	77.57%	1.000000	2096.000000

Tag Rank vs Coefficient Magnitude

Tag rank vs max coefficient magnitude — Scatter plot showing the relationship between tag battle ranking and maximum absolute coefficient value across all taxonomies. Shows which tags have the strongest influence in the model.

About p-adic loss

P-adic loss measures the distance between predicted and true taxonomy using p-adic metric (base 79). Lower values indicate closer predictions in the taxonomy hierarchy. This metric is shared with the umllr model for comparison.