pab1 · Linear

reference_pab1_lr_randomf2_20261104-162134

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	0.6479	0.9095	0.9158	0.8271	2664.0000	0.2203	1.0000	0.8000	0.5508	1.5204	0.2000	0.8238	0.7800	0.2831	1.5204	0.1600	0.7998	0.7400	0.1859	1.5204	0.1400	0.7954	0.7143	0.1352	1.5204	0.1714	0.8211
validation	0.7456	0.8939	0.9024	0.7990	917.0000	0.1510	78.0000	0.3000	-0.4799	0.5007	0.0000	0.0000	0.5038	0.4400	-0.1228	0.5166	0.0600	0.0000	0.6957	0.4900	-0.0635	1.1615	0.1300	0.0000	0.7527	0.4512	-0.0787	1.1615	0.1220	0.0000	0.7363
test	0.7424	0.8970	0.9039	0.8044	935.0000	0.1433	1241.0000	0.6000	-0.1928	0.6496	0.0000	0.0000	0.5898	0.3400	-0.2043	0.9945	0.0800	0.0000	0.6484	0.5200	-0.0895	0.9945	0.1000	0.0000	0.7290	0.4756	-0.1160	0.9945	0.0732	0.0000	0.7084

Loss per epoch

training validation

Config

name: reference_pab1_lr_randomf2
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: random
  split_fold: 2
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7