pepijn 22c9c4905e fix(pi052): avoid dense CE over padded tokens ...

Select only supervised text and FAST action-code positions before cross-entropy to avoid full-vocabulary loss tensors over padded sequences.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-05-18 18:40:34 +00:00

..

test_pi052_attention_masking.py

fix(pi052): avoid dense CE over padded tokens

2026-05-18 18:40:34 +00:00

test_pi052_fast_action_loss.py

fix(pi052): avoid dense CE over padded tokens

2026-05-18 18:40:34 +00:00

test_pi052_text_processor.py

fix(pi052): handle batched rendered messages

2026-05-18 17:41:58 +00:00