avgfp · Fully connected

reference_avgfp_fc_contiguousf1_20261104-153929

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	0.3560	0.8175	0.6916	0.4794	1898.0000	0.1734	3887.0000	0.5000	3.7512	4.0042	0.6330	0.4600	3.6803	4.0193	0.0600	0.5966	0.4500	3.6811	4.0193	0.0500	0.6284	0.4636	3.6844	4.0193	0.0545	0.6375
validation	0.5159	-0.1372	-0.1395	-0.0337	142.0000	-0.0486	49.0000	0.1000	3.0301	3.7607	0.0000	-0.4935	0.1400	2.9586	3.9612	0.0600	0.0000	-0.7130	0.1300	3.0348	3.9612	0.1100	0.0000	-0.6110	0.0909	2.8991	3.7607	0.0000	0.0000	-0.7189
test	1.3498	-0.0228	-0.0262	-0.3426	60.0000	0.0346	489.0000	0.0000	2.3259	3.6876	0.0000	-0.4796	0.0800	2.5497	3.8678	0.0600	0.0000	-0.2993	0.0900	2.5845	3.8678	0.1400	0.0000	-0.2751	0.0000	1.8586	3.6876	0.0000	0.0000	-0.8920

Loss per epoch

training validation

Config

name: reference_avgfp_fc_contiguousf1
task: dms
data:
  dataset: avgfp
  encoding: one_hot,aa_index
  split_dir: null
  split_scheme: contiguous
  split_fold: 1
model:
  name: fcn
  hidden:
  - 100
  - 100
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 32
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7