bgl3 · Linear

reference_bgl3_lr_mr5_randomf0_20261104-221645

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	0.8170	0.7842	0.7963	0.5649	134.0000	0.1654	312.0000	0.1000	-0.1850	0.1391	0.6388	0.2000	-0.2394	0.5199	0.0800	0.7192	0.1600	-0.3072	0.5199	0.1200	0.7294	0.2059	-0.2279	0.3940	0.0588	0.6986
validation	1.2168	0.6132	0.6170	0.3596	37.0000	0.1245	42.0000	0.0000	-0.9840	-0.0549	0.3349	0.1000	-0.9165	0.6710	0.1200	0.4251	0.0900	-0.8192	0.6710	0.2300	0.5110	0.0909	-0.8879	0.0726	0.0000	0.3823
test	1.1842	0.5973	0.5871	0.3478	46.0000	0.0485	335.0000	0.1000	-1.0727	0.0094	0.2478	0.1200	-0.8463	0.7630	0.1200	0.4252	0.0900	-0.8703	0.7630	0.2000	0.4418	0.1818	-0.9610	0.1561	0.0000	0.3038

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5_randomf0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  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