bgl3 · Linear

reference_bgl3_lr_mr5plm_randomf0_20261104-222243

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	0.5593	0.8411	0.8568	0.7021	134.0000	0.0789	160.0000	0.3000	-0.0257	0.3302	0.7066	0.3200	-0.0880	0.5199	0.1400	0.7944	0.2600	-0.1136	0.7042	0.2000	0.8318	0.4118	-0.0252	0.5199	0.1765	0.7958
validation	0.9057	0.7236	0.7503	0.5234	37.0000	0.1143	118.0000	0.0000	-0.3514	-0.0549	0.6338	0.1600	-0.3768	0.5578	0.1600	0.7206	0.1200	-0.3601	0.5578	0.2700	0.7795	0.0000	-0.3613	-0.0549	0.0000	0.6325
test	0.9534	0.6922	0.7201	0.4750	46.0000	0.0657	249.0000	0.2000	-0.4524	0.1248	0.5377	0.1000	-0.4843	0.1579	0.1400	0.6285	0.1200	-0.4720	0.2838	0.2500	0.6819	0.1818	-0.4124	0.1248	0.0000	0.5634

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5plm_randomf0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: random
  split_fold: 0
  min_reads: 5
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7