bgl3 · Linear

reference_bgl3_lr_mr5plm_modulof0_20261104-222315

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	1.2605	0.5422	0.5585	0.2387	109.0000	0.0797	800.0000	0.0000	-0.7208	-0.0677	0.3556	0.1200	-0.6008	0.3961	0.0400	0.4813	0.0900	-0.6246	0.3961	0.0900	0.4995	0.0690	-0.5382	0.3961	0.0345	0.4900
validation	0.7620	0.5784	0.5914	0.3249	47.0000	-0.1317	214.0000	0.1000	-0.2432	0.1391	0.4853	0.1200	-0.2971	0.1391	0.1400	0.5968	0.1200	-0.3326	0.2216	0.2700	0.6276	0.1429	-0.3102	0.1391	0.0000	0.4100
test	0.8636	0.5021	0.5288	0.2521	49.0000	-0.0599	111.0000	0.2000	-0.7366	0.2173	0.2127	0.1400	-0.6987	0.3088	0.1400	0.2891	0.1200	-0.6398	0.3088	0.2300	0.3751	0.2857	-0.8500	0.2173	0.0000	0.1326

Loss per epoch

training validation

Config

name: reference_bgl3_lr_mr5plm_modulof0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 0
  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