Abstract
Fine-tuning Large Language Models (LLMs) on multi-turn reasoning datasets requires N (number of turns) separate forward passes per conversation due to reasoning token visibility constraints, as reasoning tokens for a turn are discarded in subsequent turns. We propose duplicating response tokens along with a custom attention mask to enable single-pass processing of entire conversations. We prove our method produces identical losses to the N-pass approach while reducing time complexity from to and maintaining the same memory complexity for a transformer based model. Our approach achieves significant training speedup while preserving accuracy. Our implementation is available online (https://github.com/devrev/One-Pass-to-Reason).