PCLR Fold 2

Back to PCLR overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	10.13%
Test F1 score	0.1037
Hierarchical loss	0.77274109
P-adic loss (total)	685.25638976
P-adic loss (mean)	0.74646666
Prime base	79
Training samples	3,662
Test samples	918
Trained at	2026-08-28T05:31:32+10:00

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	93	10.13%	0.000000	0.000000
p^4	12	1.31%	0.000000	0.000000
p^3	10	1.09%	0.000002	0.000020
p^2	20	2.18%	0.000160	0.003205
p^1	99	10.78%	0.012658	1.253165
p^0	684	74.51%	1.000000	684.000000

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.