PCLR Fold 1

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	6.01%
Test F1 score	0.0582
Hierarchical loss	0.75738953
P-adic loss (total)	2161.51451932
P-adic loss (mean)	0.81198893
Prime base	79
Training samples	10,897
Test samples	2,662
Trained at	2026-05-25T05:31:31+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	160	6.01%	0.000000	0.000000
p^4	7	0.26%	0.000000	0.000000
p^3	88	3.31%	0.000002	0.000178
p^2	129	4.85%	0.000160	0.020670
p^1	118	4.43%	0.012658	1.493671
p^0	2,160	81.14%	1.000000	2160.000000

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.