avgfp · Sequence CNN

reference_avgfp_cnn_modulof3_20261104-160840

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	0.2994	0.8310	0.7335	0.6378	1547.0000	0.1876	4702.0000	0.5000	3.7523	3.9540	0.6834	0.4400	3.6819	4.1136	0.0800	0.6633	0.4900	3.7023	4.1136	0.0800	0.7148	0.4860	3.7013	4.1136	0.0748	0.7167
validation	0.5210	-0.0638	-0.0209	-0.0391	152.0000	-0.0778	437.0000	0.0000	1.3952	1.6298	0.0000	-3.1987	0.0400	2.7626	3.7538	0.0000	0.0000	-1.1093	0.1100	3.0122	3.8516	0.0800	0.0000	-0.6743	0.0000	1.3924	1.6298	0.0000	0.0000	-3.1471
test	0.7278	-0.0798	-0.0999	-0.0343	111.0000	-0.0753	346.0000	0.0000	2.1194	3.5173	0.0000	-1.4901	0.0400	2.2083	3.7396	0.0000	0.0000	-1.5573	0.0900	2.6594	3.8921	0.0700	0.0000	-0.8983	0.0000	1.8497	3.5173	0.0000	0.0000	-1.8128

Loss per epoch

training validation

Config

name: reference_avgfp_cnn_modulof3
task: dms
data:
  dataset: avgfp
  encoding: one_hot,aa_index
  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