avgfp · Sequence CNN

reference_avgfp_cnn_plm_modulof3_20261105-035752

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	0.7383	0.5582	0.5325	0.1068	1547.0000	0.0262	41.0000	0.2000	3.6501	4.0042	0.5798	0.4000	3.7151	4.1145	0.0800	0.6998	0.3600	3.6948	4.1145	0.0700	0.7063	0.3458	3.6888	4.1145	0.0748	0.7022
validation	0.5052	0.1395	0.1989	-0.0075	152.0000	0.0123	118.0000	0.2000	3.6166	3.7398	0.4733	0.2400	3.6074	3.9015	0.1000	0.5414	0.2700	3.5920	3.9015	0.1800	0.5549	0.1250	3.6381	3.7398	0.0000	0.4998
test	0.7251	0.2733	0.2128	-0.0304	111.0000	-0.0045	102.0000	0.3000	3.4644	3.7924	0.3805	0.2200	3.4334	3.7924	0.0400	0.3845	0.1800	3.3849	3.9348	0.1600	0.3281	0.1429	3.3563	3.7390	0.0000	0.2237

Loss per epoch

training validation

Config

name: reference_avgfp_cnn_plm_modulof3
task: dms
data:
  dataset: avgfp
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 3
model:
  name: cnn
  conv:
  - - 128
    - 3
  - - 128
    - 3
  - - 128
    - 3
  - - 128
    - 3
  - - 128
    - 3
  hidden:
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 64
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7