PCLR Fold 2

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	7.72%
Test F1 score	0.0858
Hierarchical loss	0.78713389
P-adic loss (total)	990.66680734
P-adic loss (mean)	0.54223690
Prime base	79
Training samples	7,283
Test samples	1,827
Trained at	2026-03-20T05:30:27+11:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	141	7.72%	0.000000	0.000000
p^4	2	0.11%	0.000000	0.000000
p^3	43	2.35%	0.000002	0.000087
p^2	369	20.20%	0.000160	0.059125
p^1	285	15.60%	0.012658	3.607595
p^0	987	54.02%	1.000000	987.000000

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.