Trainer warning with the new version

[John6666]

Maybe this?

Tokenizer deprecating in ORPO

Dear all, I was training an LLM using ORPO based on the guides by Maxime Labonne. Unfortunately, I encountered the following error on the code below: Trainer.tokenizer is now deprecated. You should use Trainer.processing_class instead. Trying to resolve it by using the processing_class in the way suggested by Gemini/ChatGPT did not resolve the problem. Does anyone have an idea how to resolve this? Kind regards, Ben orpo_args = ORPOConfig( learning_rate=8e-6, beta=0.1, lr_sched…