Multiple tasks for one fine-tuned LLM

Hi there! If you want to fine-tune an LLM on your own dataset but want it to perform multiple tasks, what would the best procedure be?

  1. Fine-tune a pre-trained model on your own dataset for one of the specific tasks.
  2. Fine-tune your model.base_model of your own fine-tuned model on another specific task (and repeat) (see reference question).


  1. Fine-tune a pre-trained model on your own dataset for one of the specific tasks.
  2. Fine-tune that same pre-trained model on your own dataset with another one of the specific tasks (and repeat)

Or would it be better to create one model with multiple task heads (see this Medium blog) instead of fine-tuning the model for each task?


I have same question. Is it better to combine datasets from multiple tasks train them once? Of better to train each dataset separately and get lora weights and then merge with base weights one-by-one afterward? Thanks.

Found answer myself:

The approach to fine-tuning a Language Model (LLM) for multiple tasks depends on various factors, including the size of your datasets, the similarity of the tasks, and your available computational resources. Here are two common approaches:

  1. Multi-Task Training (Combined Datasets):

    • If you have multiple datasets for different tasks and these tasks share some similarities (e.g., all text classification tasks), you can combine them into a single dataset.
    • Multi-task training on a combined dataset can lead to a model that generalizes well across different tasks. It allows the model to learn shared representations and potentially perform better on each task.
    • However, combining datasets may introduce some noise or task-specific patterns that could negatively impact performance on individual tasks.
  2. Task-Specific Fine-Tuning (Sequential Training):

    • Alternatively, you can fine-tune your LLM separately for each task. Train the model on one task, save the weights (e.g., LoRA weights), and then fine-tune the model for the next task using the base weights combined with the previously saved LoRA weights.
    • This approach can be useful when tasks are significantly different or when you have limited computational resources. It allows you to fine-tune incrementally and retain task-specific knowledge.
    • However, it may require more manual intervention to manage the training process for each task.

Consider these factors when deciding which approach to take:

  • Data Size: If you have a large amount of data for each task, multi-task training on combined datasets can be effective. If data is limited, task-specific fine-tuning may be better.

  • Task Similarity: If tasks are closely related, multi-task training can benefit from shared representations. If tasks are dissimilar, task-specific fine-tuning might be more appropriate.

  • Computational Resources: Multi-task training can be computationally intensive, so consider your hardware limitations.

  • Evaluation Metrics: Evaluate both approaches on your specific tasks using appropriate evaluation metrics to determine which works better in practice.

  • Experiment: It’s often beneficial to experiment with both approaches to see which one yields better results for your specific use case.

The choice between these approaches can vary based on your specific requirements and constraints.