Card: list the training data (datasets:, base_model:) and add a Training data section

Follow-up to braindecode PR #1493: `from_pretrained` reads `datasets:` into `model.card_data`. Ids: MOABB names, NEMAR nm/on ids, OpenNeuro ds ids; evidence per checkpoint.

README.md

@@ -7,7 +7,7 @@ tags:
   - dance
   - p300
 datasets:
-  - BI2014a
+- nm000244
 ---
 
 # DANCE — BI2014a P300 event-detection checkpoint
@@ -68,3 +68,21 @@ model.load_state_dict(
 - Loss: `braindecode.training.DanceLoss` (matched-only IoU normalization).
 
 Reproduce with `train_checkpoint.py` in this repository.
+
+<!-- braindecode:training-data -->
+## Training data
+
+The data that shaped these weights. The ids are the `datasets:` field of this card,
+which braindecode reads into `model.card_data.datasets` when you call
+`from_pretrained` (MOABB class names for MOABB datasets, OpenNeuro / NEMAR
+accessions, Hub ids otherwise). `nm`/`on` ids are datasets on [NEMAR](https://nemar.org)
+(`on` = NEMAR's copy of the OpenNeuro dataset with the same number). Rows marked
+`private:` are data the authors did not release; they are not in `datasets:`.
+
+| `datasets:` id | Dataset | Stage | Modality |
+|---|---|---|---|
+| [`nm000244`](https://nemar.org/dataset/nm000244) | [Brain Invaders 2014a P300 dataset (MOABB BI2014a)](https://moabb.neurotechx.com/docs/generated/moabb.datasets.BI2014a.html) | training | EEG |
+
+- Supervised DANCE event detection, cross-subject. Gradient updates on BI2014a subjects 1, 2, 4, 5, 6, 7, 8, 9 (all their sessions as loaded by MOABBDataset); subject 3 is the held-out subject but its F1-event is used to keep the best epoch (torch.save on improvement), so subject 3 selected the checkpoint. 32 s windows at 128 Hz, 120 epochs per card (script default 100).
+- Sources: https://huggingface.co/braindecode/plot_dance_event_detection/resolve/main/train_checkpoint.py; W/cards-orig/plot_dance_event_detection.md; W/bd/examples/applied_examples/plot_dance_event_detection.py.
+