run_2_soup_trainer_output.txt

=================================================================
BASE TIER PATCHWORK SOUP — CALIBRATED
  3 experts × 768-d → 256 anchors × 128-d
  Device: cuda
=================================================================

=================================================================
PHASE 0: LOAD DATA
=================================================================
  Train: 118,287  Val: 5,000
  clip_l14_openai                loaded
  dinov2_b14                     loaded
  siglip_b16_384                 loaded

=================================================================
PHASE 1: GPA ALIGNMENT AT 768-d
=================================================================
  GPA iter 1: delta=2.42780352
  GPA iter 5: delta=0.00656253
  GPA iter 10: delta=0.00082383
  GPA iter 15: delta=0.00027677
  GPA iter 20: delta=0.00013823
  cos(consensus, clip_l14_openai): 0.9723
  cos(consensus, dinov2_b14): 0.9650
  cos(consensus, siglip_b16_384): 0.9747
  Consensus CV at 768-d: 0.2793

=================================================================
PHASE 2: PROJECT TO 128-d + CALIBRATE
=================================================================
  PCA 768→128: variance retained = 0.9988
  Consensus CV at 128-d: 0.2731
  Val consensus: torch.Size([5000, 128])

=================================================================
PHASE 3: PER-EXPERT PROCRUSTES CALIBRATION
=================================================================
  clip_l14_openai                cos=0.6245 svd: min=20.4983 max=58.0336
  dinov2_b14                     cos=0.6199 svd: min=18.0785 max=70.0417
  siglip_b16_384                 cos=0.6263 svd: min=20.0792 max=60.3250

=================================================================
PHASE 4: BUILD + INITIALIZE
=================================================================
  ✓ clip_l14_openai projector initialized (cos=0.6245)
  ✓ dinov2_b14 projector initialized (cos=0.6199)
  ✓ siglip_b16_384 projector initialized (cos=0.6263)
  ✓ Constellation seeded from consensus
    clip proj→consensus cos: 0.6209
    dino proj→consensus cos: 0.6156
    siglip proj→consensus cos: 0.6222
  Init: cos=0.6720 cv=0.1535 active_anchors=87/256
  Parameters: 799,952
  CV target: 0.2731

=================================================================
PHASE 5: TRAINING
  20 epochs, lr=0.001, CV target=0.2731
=================================================================
  E 1: mAP=0.788 F1=0.731 R@1=0.971 cos=0.806 cv=0.1213 anchors=226/256 nce=0.999 loss=0.1676 ★
  E 2: mAP=0.803 F1=0.742 R@1=0.971 cos=0.809 cv=0.1178 anchors=200/256 nce=0.999 loss=0.1459 ★
  E 3: mAP=0.810 F1=0.735 R@1=0.973 cos=0.808 cv=0.1197 anchors=161/256 nce=0.999 loss=0.1431 ★
  E 4: mAP=0.817 F1=0.752 R@1=0.971 cos=0.811 cv=0.1262 anchors=131/256 nce=0.999 loss=0.1404 ★
  E 5: mAP=0.823 F1=0.755 R@1=0.971 cos=0.812 cv=0.1232 anchors=113/256 nce=0.999 loss=0.1389 ★
  E 6: mAP=0.825 F1=0.755 R@1=0.972 cos=0.815 cv=0.1105 anchors=104/256 nce=0.999 loss=0.1379 ★
  E 7: mAP=0.827 F1=0.767 R@1=0.970 cos=0.814 cv=0.1125 anchors=101/256 nce=0.999 loss=0.1369 ★
  E 8: mAP=0.829 F1=0.763 R@1=0.971 cos=0.815 cv=0.1239 anchors=99/256 nce=0.999 loss=0.1361 ★
  E 9: mAP=0.832 F1=0.764 R@1=0.972 cos=0.815 cv=0.1164 anchors=98/256 nce=0.999 loss=0.1355 ★
  E10: mAP=0.833 F1=0.765 R@1=0.968 cos=0.814 cv=0.1166 anchors=99/256 nce=0.999 loss=0.1345 ★
  E11: mAP=0.834 F1=0.763 R@1=0.971 cos=0.814 cv=0.1214 anchors=98/256 nce=0.999 loss=0.1346 ★
  E12: mAP=0.833 F1=0.764 R@1=0.973 cos=0.813 cv=0.1200 anchors=95/256 nce=0.999 loss=0.1343
  E13: mAP=0.836 F1=0.761 R@1=0.972 cos=0.813 cv=0.1081 anchors=94/256 nce=0.999 loss=0.1338 ★
  E14: mAP=0.836 F1=0.772 R@1=0.973 cos=0.812 cv=0.1170 anchors=95/256 nce=0.999 loss=0.1334
  E15: mAP=0.835 F1=0.774 R@1=0.970 cos=0.812 cv=0.1223 anchors=95/256 nce=0.999 loss=0.1338
  E16: mAP=0.837 F1=0.777 R@1=0.968 cos=0.812 cv=0.1225 anchors=96/256 nce=1.000 loss=0.1339 ★
  E17: mAP=0.834 F1=0.772 R@1=0.973 cos=0.811 cv=0.1089 anchors=95/256 nce=0.999 loss=0.1327
  E18: mAP=0.834 F1=0.770 R@1=0.973 cos=0.812 cv=0.1156 anchors=95/256 nce=0.999 loss=0.1321
  E19: mAP=0.834 F1=0.773 R@1=0.970 cos=0.811 cv=0.1224 anchors=96/256 nce=0.999 loss=0.1328
  E20: mAP=0.835 F1=0.770 R@1=0.971 cos=0.812 cv=0.1159 anchors=96/256 nce=0.999 loss=0.1328

  Best mAP: 0.837
  CV target: 0.2731

=================================================================
DONE
=================================================================