When we use a sequence of messages for training (e.g. user message #1, assistant message #1, user message #2, assistant message #2), is the model trained to generate only the last message (i.e. assistant message #2) of the assistant in the sequence, and all previous messages are used as context, or is the model trained to generate each assistant message separately (i.e. both assistant message #1 and assistant message #2)? That is, what is the target of the model?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How is the prompt + answer handled during training | 0 | 123 | March 20, 2024 | |
| How to provide a target and input separately for Trainer? | 0 | 371 | February 16, 2023 | |
| How does GPT decide to stop generating sentences without EOS token? | 13 | 25349 | August 19, 2024 | |
| SFT for chatbot - `text` column | 2 | 875 | March 8, 2024 | |
| Fine-tune MT5ConditionalGeneration for question generation | 0 | 508 | January 4, 2022 |