- process_list_field returns List[List[int]] preserving per-response boundaries - GRPODataset rewritten to record-level __getitem__ (no windowing/stride) - grpo_collate_fn pads variable-length responses into [B, G, R] tensors - JsonlStore detects nested List[List[int]] and stores List[Tensor] per record - Store._normalize skips nested-list keys from cumsum bookkeeping - Pipeline._flush handles nested lists without cross-record flattening - Export grpo_collate_fn from astrai.dataset - 6 new GRPO tests + 2 updated builder tests, 114 total pass |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| dataset.py | ||
| sampler.py | ||
| storage.py | ||