This is catastrophic forgetting: updating weights toward the new data erases some of what the model learned before.
Reduce it with LoRA or other parameter-efficient methods, a lower learning rate and fewer epochs, mixing in some general instruction data (replay), and regularization toward the base model.
Always evaluate on a broad regression suite (general capabilities, safety, your core tasks), not only on the new task, and keep the base model as a fallback.
Loading…