pab1 · Linear

reference_pab1_lr_contiguousf0_20261104-145743

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	1.9087	0.6852	0.6027	0.4128	3428.0000	0.0541	2582.0000	0.1000	-1.3914	0.0004	0.0000	0.0417	0.1600	-0.6261	0.4516	0.0000	0.3596	0.2200	-0.4058	1.1524	0.0100	0.4715	0.2597	-0.2892	1.1524	0.0260	0.5571
validation	3.6220	0.1483	0.1660	-0.0091	196.0000	0.1051	935.0000	0.1000	-3.0037	0.2658	0.0000	0.0000	-0.3784	0.1400	-2.1637	0.3670	0.0600	0.0000	-0.0517	0.1000	-2.2233	0.3670	0.0500	0.0000	-0.0798	0.1250	-2.4549	0.2658	0.0000	0.0000	-0.1692
test	4.7132	-0.0034	0.0233	-0.2716	222.0000	0.0529	8.0000	0.1000	-3.6689	0.6320	0.1000	0.0000	-0.3444	0.0600	-2.7961	0.6320	0.0200	0.0000	-0.0647	0.0400	-2.9762	0.6320	0.0200	0.0000	-0.1299	0.0612	-2.8443	0.6320	0.0204	0.0000	-0.0810

Loss per epoch

training validation

Config

name: reference_pab1_lr_contiguousf0
task: dms
data:
  dataset: pab1
  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: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7