PCLR Fold 0

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	5.74%
Test F1 score	0.0596
Hierarchical loss	0.75918283
P-adic loss (total)	2131.59109389
P-adic loss (mean)	0.80528564
Prime base	79
Training samples	10,625
Test samples	2,647
Trained at	2026-05-20T05:31:00+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	152	5.74%	0.000000	0.000000
p^5	1	0.04%	0.000000	0.000000
p^4	27	1.02%	0.000000	0.000001
p^3	80	3.02%	0.000002	0.000162
p^2	133	5.02%	0.000160	0.021311
p^1	124	4.68%	0.012658	1.569620
p^0	2,130	80.47%	1.000000	2130.000000

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.