PCLR Fold 1

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	9.38%
Test F1 score	0.1022
Hierarchical loss	0.76786652
P-adic loss (total)	798.29264640
P-adic loss (mean)	0.83242195
Prime base	79
Training samples	3,621
Test samples	959
Trained at	2026-08-28T05:31:26+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	90	9.38%	0.000000	0.000000
p^4	7	0.73%	0.000000	0.000000
p^3	32	3.34%	0.000002	0.000065
p^2	9	0.94%	0.000160	0.001442
p^1	23	2.40%	0.012658	0.291139
p^0	798	83.21%	1.000000	798.000000

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.