bgl3 · Linear

reference_bgl3_lr_modulof0_20261104-144132

Metrics

Set	mse	pearsonr	spearmanr	r2	above_wt_n	above_wt_spearmanr	budget_to_max	hit_rate_at_10	mean_at_10	max_at_10	captured_at_10	hit_rate_at_50	mean_at_50	max_at_50	precision_at_50	captured_at_50	hit_rate_at_100	mean_at_100	max_at_100	precision_at_100	captured_at_100	hit_rate_at_1pct	mean_at_1pct	max_at_1pct	precision_at_1pct	captured_at_1pct
train	1.7672	0.1699	0.1555	0.0170	3841.0000	0.0175	4115.0000	0.5000	-0.3927	1.2150	-0.0061	0.6200	0.2535	1.9459	0.0000	0.2122	0.6400	0.3271	2.2610	0.0100	0.2504	0.6273	0.3064	2.2610	0.0091	0.2450
validation	1.5660	0.0748	0.0778	-0.0003	424.0000	-0.0175	427.0000	0.4000	0.1941	1.8690	0.0000	0.2179	0.3400	-0.1732	1.9459	0.0400	0.0000	0.1070	0.3800	-0.1081	2.0841	0.1400	0.0000	0.1500	0.4000	0.0908	1.8690	0.0000	0.0000	0.1880
test	1.5768	-0.0972	-0.0796	-0.0468	338.0000	-0.0161	989.0000	0.1000	-1.4710	0.4959	0.0000	-0.3305	0.1800	-0.9621	1.5945	0.0200	0.0000	-0.1685	0.1900	-0.9958	1.5945	0.0500	0.0000	-0.2020	0.0769	-1.7120	0.4959	0.0000	0.0000	-0.4266

Loss per epoch

training validation

Config

name: reference_bgl3_lr_modulof0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: modulo
  split_fold: 0
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7