PCLR Fold 4

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	10.65%
Test F1 score	0.1174
Hierarchical loss	0.76642590
P-adic loss (total)	744.19344317
P-adic loss (mean)	0.82596387
Prime base	79
Training samples	3,679
Test samples	901
Trained at	2026-08-28T05:31:47+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	96	10.65%	0.000000	0.000000
p^4	2	0.22%	0.000000	0.000000
p^3	22	2.44%	0.000002	0.000045
p^2	22	2.44%	0.000160	0.003525
p^1	15	1.66%	0.012658	0.189873
p^0	744	82.57%	1.000000	744.000000

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.