How do I resume training from a saved checkpoint?

[daegonYu]

I have fine-tuned the reranker through this github. I would like to continue learning from the saved checkpoint. Can you give me some instructions on how to do that?

[staoxiao]

You can pass the fine-tuned model to --model_name_or_path

[daegonYu]

This method is not a method to continue learning from the model's interrupted LR and train dataset, but a method to additionally learn from an initialized state, right?

[staoxiao]

This method is not a method to continue learning from the model's interrupted LR and train dataset, but a method to additionally learn from an initialized state, right?

Yes. The current script doesn't implement the function to resume training from the previous state.

[daegonYu]

Thank you for your reply.