pab1 · Fully connected

reference_pab1_fc_plm_contiguousf3_20261105-040838

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	1.0543	0.9174	0.9168	0.7343	1489.0000	0.0127	2793.0000	0.1000	-0.2967	0.0347	0.6657	0.3000	-0.1543	0.5163	0.0200	0.7534	0.3500	-0.1034	0.5163	0.0300	0.7921	0.4019	-0.1023	0.5163	0.0467	0.8174
validation	0.8291	0.7608	0.6185	0.5555	931.0000	0.0321	1334.0000	0.2000	-0.2098	0.2331	0.3911	0.1800	-0.3550	0.8601	0.0400	0.3689	0.2500	-0.3056	0.8601	0.0200	0.4287	0.1556	-0.3679	0.8601	0.0222	0.3577
test	0.8526	0.8245	0.6979	0.6640	383.0000	-0.0467	2006.0000	0.1000	-0.3209	0.0138	0.4363	0.2000	-0.2094	0.4637	0.0400	0.5655	0.2300	-0.1733	0.4974	0.0900	0.6349	0.1562	-0.2248	0.4333	0.0000	0.5336

Loss per epoch

training validation

Config

name: reference_pab1_fc_plm_contiguousf3
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: contiguous
  split_fold: 3
model:
  name: fcn
  hidden:
  - 100
  - 100
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7