bgl3 · Linear

reference_bgl3_lr_plm_modulof0_20261104-175049

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	1.5599	0.3649	0.3163	0.1324	3841.0000	-0.0381	1245.0000	0.4000	0.2548	1.3581	0.0000	0.1894	0.5200	0.1897	1.7856	0.0000	0.1906	0.5400	0.2680	2.3136	0.0200	0.2292	0.5273	0.2219	2.3136	0.0182	0.2145
validation	1.4113	0.3247	0.2818	0.0985	424.0000	-0.0837	313.0000	0.8000	0.7674	1.9459	0.0000	0.4156	0.3600	0.0987	1.9459	0.0600	0.2171	0.3200	-0.0217	2.4113	0.1000	0.1894	0.6667	0.5611	1.9459	0.0000	0.3554
test	1.4262	0.2912	0.2752	0.0531	338.0000	-0.2108	1141.0000	0.5000	0.0279	2.3637	0.1000	0.2167	0.3200	-0.3968	2.3637	0.0200	0.0718	0.2700	-0.4381	2.3637	0.0500	0.0600	0.4615	-0.2463	2.3637	0.0769	0.1189

Loss per epoch

training validation

Config

name: reference_bgl3_lr_plm_modulof0
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 0
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7