bgl3 · Linear

reference_bgl3_lr_mr5plm_modulof2_20261104-222707

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	1.1689	0.5551	0.5808	0.2666	143.0000	-0.0624	667.0000	0.3000	-0.9991	0.2173	0.0000	0.1640	0.1000	-0.7997	0.2173	0.0200	0.3192	0.1000	-0.7507	0.2173	0.0600	0.3771	0.1111	-1.0109	0.2173	0.0000	0.1814
validation	0.7744	0.4841	0.4783	0.2278	44.0000	0.1268	362.0000	0.1000	-0.6418	0.3961	0.1000	0.1966	0.1200	-0.5373	0.3961	0.1200	0.3518	0.1100	-0.4963	0.5199	0.2500	0.4317	0.1429	-0.7401	0.3961	0.1429	0.1176
test	0.9948	0.4139	0.4938	0.1532	23.0000	-0.0301	106.0000	0.1000	-1.9184	0.1022	0.0000	-0.5931	0.0800	-0.9773	0.2821	0.1200	0.1104	0.0800	-0.8179	0.2821	0.2700	0.2676	0.1250	-1.9927	0.1022	0.0000	-0.6336

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5plm_modulof2
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 2
  min_reads: 5
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7