bgl3 · Fully connected
reference_bgl3_fc_modulof2_20261104-163122
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 | tie_share_at_10 | captured_at_10 | hit_rate_at_50 | mean_at_50 | max_at_50 | precision_at_50 | tie_share_at_50 | captured_at_50 | hit_rate_at_100 | mean_at_100 | max_at_100 | precision_at_100 | tie_share_at_100 | captured_at_100 | hit_rate_at_1pct | mean_at_1pct | max_at_1pct | precision_at_1pct | tie_share_at_1pct | captured_at_1pct |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| train | 1.8054 | 0.5241 | 0.5165 | 0.0124 | 3477.0000 | 0.1475 | 1717.0000 | 0.9000 | 1.3324 | 2.3637 | 0.0000 | 0.0000 | 0.5192 | 0.8200 | 0.9120 | 2.3637 | 0.0400 | 0.0000 | 0.4389 | 0.7700 | 0.7562 | 2.4113 | 0.0600 | 0.0000 | 0.4068 | 0.7579 | 0.7573 | 2.4113 | 0.0526 | 0.0000 | 0.4056 |
| validation | 1.3788 | 0.0208 | 0.0104 | 0.0000 | 437.0000 | 0.0479 | 909.0000 | 0.4000 | -0.2778 | 1.9459 | 0.0000 | 0.0000 | 0.0439 | 0.3800 | -0.3282 | 3.0445 | 0.0600 | 0.0000 | 0.0346 | 0.3700 | -0.3336 | 3.0445 | 0.0800 | 0.0000 | 0.0367 | 0.3750 | -0.2651 | 3.0445 | 0.0625 | 0.0000 | 0.0504 |
| test | 1.5552 | -0.0165 | -0.0364 | -0.0089 | 432.0000 | 0.0414 | 553.0000 | 0.1000 | -1.4285 | 1.3581 | 0.0000 | 0.0000 | -0.3139 | 0.1400 | -1.2277 | 1.8690 | 0.0200 | 0.0000 | -0.2827 | 0.1700 | -1.0104 | 1.8690 | 0.0400 | 0.0000 | -0.2135 | 0.0588 | -1.4444 | 1.3581 | 0.0000 | 0.0000 | -0.3311 |
Loss per epoch
training
validation
Config
name: reference_bgl3_fc_modulof2 task: dms data: dataset: bgl3 encoding: one_hot,aa_index split_dir: null split_scheme: modulo split_fold: 2 model: name: fcn hidden: - 100 - 100 dropout: 0.2 train: epochs: 300 batch_size: 32 learning_rate: 0.0001 patience: 15 min_delta: 1.0e-05 seed: 7