bgl3 · Linear

reference_bgl3_lr_mr5_randomf2_20261104-222045

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	precision_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	0.5870	0.8388	0.8405	0.6848	124.0000	0.1673	1.0000	0.5000	0.1000	0.9971	0.1000	0.7556	0.3200	-0.1112	0.9971	0.1600	0.7727	0.2600	-0.1429	0.9971	0.2200	0.8096	0.3529	-0.1069	0.9971	0.0882	0.7451
validation	1.1935	0.6042	0.6099	0.3647	40.0000	0.1725	103.0000	0.0000	-0.8751	-0.0764	0.0000	0.3992	0.0600	-0.7148	0.0925	0.0600	0.5390	0.0600	-0.6000	0.2595	0.2000	0.6386	0.0000	-0.8704	-0.0764	0.0000	0.4037
test	1.1732	0.6159	0.6256	0.3793	53.0000	-0.1054	218.0000	0.0000	-1.3858	-0.0391	0.0000	0.1325	0.1200	-0.8241	0.5199	0.1200	0.4581	0.1800	-0.8594	0.5199	0.2400	0.4689	0.0000	-1.2890	-0.0391	0.0000	0.1780

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5_randomf2
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: random
  split_fold: 2
  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