bgl3 · Linear

reference_bgl3_lr_mr5plm_randomf1_20261104-222437

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	0.6139	0.8309	0.8464	0.6690	127.0000	0.0793	12.0000	0.3000	-0.0713	0.3302	0.6859	0.2800	-0.0781	0.9971	0.1200	0.7980	0.2200	-0.1301	0.9971	0.1800	0.8218	0.3824	-0.0267	0.9971	0.1176	0.7943
validation	0.9837	0.6938	0.7264	0.4795	53.0000	-0.0198	215.0000	0.3000	-0.6864	0.1391	0.4467	0.1600	-0.4276	0.2821	0.1600	0.6702	0.2000	-0.4370	0.5199	0.3300	0.7100	0.2727	-0.6386	0.1391	0.0000	0.4734
test	0.9545	0.7131	0.7396	0.4977	37.0000	-0.0090	549.0000	0.1000	-0.4990	0.0268	0.5641	0.1000	-0.4178	0.5578	0.1000	0.6982	0.1100	-0.4362	0.5578	0.2600	0.7349	0.1818	-0.4232	0.3347	0.0909	0.6031

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5plm_randomf1
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: random
  split_fold: 1
  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