renxiaoqin

ask tuning details, like lr

1

Can you explain the learning rate Settings of Instruction-based Tuning and Conversation-based Tuning? thanks so much!

### Description Under 1 gpu setting, optimize_model can be successfully used for inference acceleration。But errors will be reported in 2 gpus, using pipeline parallel: code is : model = AutoModelForCausalLM.from_pretrained(model_path,...