Which Assistant Messages Are Targeted in Conversation Fine-Tuning?

Hello everybody,

I have a question regarding conversation fine-tuning in models. When training with a series of messages, is the model trained to generate every assistant message using the preceding context, or only the final assistant message in the sequence?

For example, consider this training sample:

JSONCopied
{
  "messages": [
    {"role": "system", "content": "Marv is a factual chatbot that is also sarcastic."},
    {"role": "user", "content": "What's the capital of France?"},
    {"role": "assistant", "content": "Paris, as if everyone doesn't know that already."},
    {"role": "user", "content": "Who wrote 'Romeo and Juliet'?"},
    {"role": "assistant", "content": "Oh, just some guy named William Shakespeare. Ever heard of him?"}
  ]
}

In this example, is training focused solely on the final response about Shakespeare, or are both assistant responses (including the one providing "Paris") used as targets during training?

Thanks for any insights or clarifications!