pab1 · Fully connected

reference_pab1_fc_contiguousf0_20261104-145725

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	1.0336	0.8420	0.8113	0.6820	3428.0000	0.0880	13502.0000	0.7000	0.1300	0.8601	0.6054	0.6600	0.1193	0.8601	0.0200	0.6649	0.6200	0.1019	0.8601	0.0200	0.6895	0.5498	0.0445	0.9715	0.0476	0.7102
validation	3.8598	-0.2456	-0.2431	-0.0753	196.0000	0.0968	1437.0000	0.0000	-2.8407	-0.2934	0.0000	-0.3142	0.0800	-2.6353	0.3317	0.0600	0.0000	-0.2522	0.0400	-2.6388	0.3317	0.0300	0.0000	-0.2627	0.0417	-2.5863	0.0301	0.0000	0.0000	-0.2230
test	4.4824	-0.1805	-0.1924	-0.2093	222.0000	0.0374	3282.0000	0.0000	-3.7061	-1.6136	0.0000	-0.3564	0.0400	-2.8377	0.0916	0.0000	0.0000	-0.0788	0.0300	-3.0683	0.2331	0.0100	0.0000	-0.1622	0.0204	-2.8969	0.0916	0.0000	0.0000	-0.0988

Loss per epoch

training validation

Config

name: reference_pab1_fc_contiguousf0
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: contiguous
  split_fold: 0
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