PCLR Fold 1

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	14.68%
Test F1 score	0.1356
Hierarchical loss	0.92243658
P-adic loss (total)	452.36922607
P-adic loss (mean)	0.65751341
Prime base	71
Training samples	2,735
Test samples	688
Trained at	2025-12-16T22:25:39+11:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	101	14.68%	0.000000	0.000000
p^4	5	0.73%	0.000000	0.000000
p^3	19	2.76%	0.000003	0.000053
p^2	86	12.50%	0.000198	0.017060
p^1	25	3.63%	0.014085	0.352113
p^0	452	65.70%	1.000000	452.000000

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 71). Lower values indicate closer predictions in the taxonomy hierarchy. This metric is shared with the umllr model for comparison.