mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-20 02:59:50 +00:00
Pepijn
15f79b5e5e
PI052TextTokenizerStep masked text_labels over the assistant turn's *content only* — the trailing newline was excluded and no EOS token was ever a supervised label. So the LM head was never given a stop signal: at inference select_message decoded to max_new_tokens, producing the runaway subtask paragraphs and the "}"}"}-style VQA tails. _format_messages now appends the tokenizer's EOS to each supervised target turn and extends that turn's span to cover it, so the EOS lands in text_labels. _shifted_ce then trains "<last content token> -> EOS" and the model learns to terminate; select_message stops on it. Inference callers (the runtime's _build_text_batch_pi052) pass no target_indices / eos_token, so no EOS is baked into the prompt — the model generates it. Verified end-to-end with the PaliGemma tokenizer: the supervised span is `<content><eos>` and the trailing newline stays unsupervised. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>