pab1 · Linear

reference_pab1_lr_plm_contiguousf3_20261105-040856

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	1.1323	0.8936	0.9263	0.7146	1489.0000	0.1161	1834.0000	0.4000	-0.0271	0.5640	0.7516	0.5000	-0.0137	0.5640	0.0400	0.8009	0.5600	0.0033	0.8505	0.0600	0.8292	0.5374	-0.0033	0.8505	0.1075	0.8529
validation	1.0924	0.6697	0.5196	0.4144	931.0000	-0.0294	1371.0000	0.2000	-0.3348	0.1090	0.3294	0.1600	-0.3632	0.7857	0.0400	0.3642	0.2300	-0.3481	0.7857	0.0400	0.4026	0.1778	-0.3478	0.7857	0.0444	0.3690
test	1.2903	0.7202	0.6263	0.4915	383.0000	0.0036	2337.0000	0.0000	-0.3411	-0.1535	0.4262	0.1400	-0.2676	0.4637	0.0400	0.5321	0.1400	-0.3074	0.4637	0.0300	0.5514	0.1250	-0.2739	0.3035	0.0000	0.5066

Loss per epoch

training validation

Config

name: reference_pab1_lr_plm_contiguousf3
task: dms
data:
  dataset: pab1
  encoding: one_hot,aa_index,plm,plm_sum
  split_dir: null
  split_scheme: contiguous
  split_fold: 3
model:
  name: lr
train:
  epochs: 300
  batch_size: 128
  learning_rate: 0.001
  patience: 15
  min_delta: 1.0e-05
  seed: 7