Add more training charts, add root config.json for download tracking

README.md

@@ -53,6 +53,22 @@ or both.
 | Throughput | ~90-110 img/s, batch 32, RTX 5090 |
 | Single-frame inference | 30.7 ms / 32.5 FPS (batch 1, eager, RTX 5090) |
 
+Train loss over the same run, log-shaped as expected for a detector trained from scratch:
+
+<img src="assets/loss_progress.svg" alt="Train loss by epoch, dropping sharply in the first few epochs then declining gradually from about 6 to 4.1 over the rest of training" width="900">
+
+AP50 (IoU 0.50, a looser localization threshold) against AP75 (IoU 0.75, stricter). Both climb
+together early on, then AP75 plateaus lower, meaning coarse localization improved faster than
+precise localization did:
+
+<img src="assets/ap50_75_progress.svg" alt="AP50 and AP75 by epoch as two lines, AP50 rising to about 0.54 and AP75 to about 0.38" width="900">
+
+AP broken out by object size. Large objects are detected far more reliably than small ones
+throughout training, a common pattern for this class of detector and one of the things the
+required ablations would need to explain:
+
+<img src="assets/ap_by_size_progress.svg" alt="AP by object size (small, medium, large) by epoch as three lines, large objects highest at about 0.49, medium at about 0.39, small lowest at about 0.18" width="900">
+
 Peak AP came at epoch 95 (0.3578), not the final epoch. That is normal late-training fluctuation,
 and `best.pt` correctly holds the epoch-95 weights rather than epoch 100's. Against the 40-50 AP
 range set as the competitiveness bar, this run falls short. It is a real result from a genuine