bgl3 · Sequence CNN

reference_bgl3_cnn_plm_modulof3_20261105-035853

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	1.2582	0.6013	0.5518	0.3568	3467.0000	0.1066	3276.0000	0.8000	1.2755	2.9405	0.1000	0.5106	0.7400	1.0418	2.9405	0.0600	0.5008	0.7200	0.8734	2.9405	0.0500	0.4665	0.7172	0.8716	2.9405	0.0505	0.4655
validation	1.2148	0.3205	0.3218	0.1026	437.0000	-0.0823	1165.0000	0.5000	0.1679	1.3581	0.0000	0.1971	0.4600	0.1897	2.3637	0.0800	0.2459	0.4000	0.0380	2.3637	0.1200	0.2015	0.4375	0.1248	1.3581	0.0000	0.1915
test	1.2583	0.3024	0.2611	0.0874	437.0000	-0.1248	883.0000	0.3000	-0.0375	1.9459	0.0000	0.1219	0.3600	-0.0263	2.1466	0.0800	0.1578	0.3600	-0.1420	3.0445	0.0900	0.1253	0.3125	-0.0316	1.9459	0.0000	0.1300

Loss per epoch

training validation

Config

name: reference_bgl3_cnn_plm_modulof3
task: dms
data:
  dataset: bgl3
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 3
model:
  name: cnn
  conv:
  - - 32
    - 17
  hidden:
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 64
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7