bgl3 · Linear

reference_bgl3_lr_contiguousf0_20261104-144931

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	1.5332	0.5334	0.4860	0.2290	6904.0000	0.1142	8298.0000	0.9000	1.4817	3.1160	0.1000	0.5296	0.8200	1.0732	3.1160	0.0200	0.4495	0.8600	1.0184	3.1160	0.0200	0.4560	0.8480	0.9191	3.1160	0.0175	0.4413
validation	1.6884	-0.0136	-0.0190	-0.0193	1203.0000	-0.0115	2764.0000	0.7000	0.2979	1.2150	0.0000	0.0000	0.2248	0.5000	0.1374	1.8690	0.0000	0.0000	0.1821	0.4500	-0.1042	1.9459	0.0400	0.0000	0.0925	0.5882	0.2191	1.7856	0.0000	0.0000	0.2080
test	2.1096	0.0733	0.0636	-0.0527	1218.0000	-0.0603	1547.0000	0.4000	-0.0538	1.4833	0.0000	0.0000	0.1779	0.3800	-0.1501	1.7856	0.0000	0.0000	0.1772	0.3900	-0.2107	3.3229	0.0200	0.0000	0.1691	0.3953	-0.0825	1.7856	0.0000	0.0000	0.1969

Loss per epoch

training validation

Config

name: reference_bgl3_lr_contiguousf0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: contiguous
  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