pab1 · Sequence CNN

reference_pab1_cnn_plm_modulof3_20261105-040103

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	1.1929	0.8359	0.8280	0.6762	1256.0000	0.0089	5070.0000	0.0000	-0.2502	-0.0019	0.5803	0.1800	-0.2295	0.3401	0.0000	0.6451	0.2200	-0.2150	0.4542	0.0100	0.6888	0.2500	-0.2059	1.0896	0.0270	0.7131
validation	1.2279	0.8191	0.7451	0.6697	234.0000	0.0215	931.0000	0.1000	-0.1519	0.2554	0.6694	0.3000	-0.2347	0.8367	0.0400	0.6950	0.3400	-0.1840	0.8367	0.1600	0.7558	0.2000	-0.2395	0.2554	0.0000	0.6446
test	1.4288	0.7779	0.7503	0.5912	223.0000	0.1280	543.0000	0.2000	-0.2175	0.3577	0.6085	0.3600	-0.1712	0.7491	0.1200	0.7089	0.3400	-0.2019	0.7491	0.1900	0.7346	0.1875	-0.2661	0.6443	0.0625	0.6097

Loss per epoch

training validation

Config

name: reference_pab1_cnn_plm_modulof3
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: modulo
  split_fold: 3
model:
  name: cnn
  conv:
  - - 128
    - 17
  - - 128
    - 17
  - - 128
    - 17
  hidden:
  - 100
  dropout: 0.2
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.0001
  patience: 15
  min_delta: 1.0e-05
  seed: 7