pab1 · Linear

reference_pab1_lr_plm_contiguousf1_20261104-182022

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	0.6480	0.9117	0.8860	0.7750	2849.0000	0.0622	864.0000	0.4000	-0.0025	0.5166	0.5416	0.5800	0.0473	0.7331	0.0000	0.6243	0.6000	0.0623	0.8601	0.0400	0.6643	0.6313	0.0806	0.8744	0.0657	0.7120
validation	2.6117	0.6213	0.6660	0.3851	475.0000	-0.0210	1660.0000	0.3000	-0.1478	0.0738	0.7229	0.2600	-0.0933	0.5226	0.0400	0.7969	0.2400	-0.1180	0.5226	0.0600	0.8159	0.2500	-0.0989	0.5226	0.0417	0.7934
test	2.5142	0.6173	0.6064	0.2995	196.0000	0.0489	1822.0000	0.1000	-0.5461	0.1870	0.5884	0.2200	-0.5066	0.4145	0.0400	0.6525	0.1900	-0.5031	0.4145	0.1100	0.6772	0.2083	-0.4495	0.2129	0.0000	0.6523

Loss per epoch

training validation

Config

name: reference_pab1_lr_plm_contiguousf1
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: contiguous
  split_fold: 1
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7