bgl3 · Linear

reference_bgl3_lr_contiguousf3_20261104-161816

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	1.6611	0.5148	0.4869	0.1576	4815.0000	0.1270	5643.0000	0.8000	0.9896	2.0174	0.4149	0.7400	0.8046	2.3637	0.0200	0.4103	0.7200	0.7620	2.3637	0.0300	0.4194	0.7319	0.7170	2.3637	0.0362	0.4154
validation	1.8061	-0.0000	-0.0025	-0.0169	1997.0000	-0.0263	2825.0000	0.5000	-0.0356	1.2150	0.0000	0.0517	0.5200	0.1030	1.9459	0.0000	0.0000	0.1132	0.5600	0.1344	2.2054	0.0200	0.0000	0.1340	0.4894	0.0474	1.9459	0.0000	0.0000	0.0911
test	1.9590	0.0548	0.0631	-0.0114	1899.0000	-0.0436	768.0000	0.4000	-1.1804	1.5945	0.0000	-0.2825	0.4800	-0.4682	1.5945	0.0000	0.0000	-0.0671	0.4800	-0.3806	1.9459	0.0000	0.0000	-0.0378	0.4694	-0.4831	1.5945	0.0000	0.0000	-0.0724

Loss per epoch

training validation

Config

name: reference_bgl3_lr_contiguousf3
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: contiguous
  split_fold: 3
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7