Sijia Chen

> I appreciate your interest in our paper. We plan to release the code organized after the NeurIPS deadline. Thanks! Waiting for this wonderful work and I hope my subsequent...

> what does `train_on_responses_only` do exactly? Could you explain a bit more? Thanks! [@danielhanchen](https://github.com/danielhanchen) [High-level idea] For the decoder-only model, the loss is computed based on the next-token prediction. Therefore,...