Closed treya-lin closed 4 months ago
max_output_length 按照transformers传递参数的方式就行了,都是通用的
max_output_length 按照transformers传递参数的方式就行了,都是通用的
我是想问 generation_config 里面的 max_new_token
,不是 max_output_length
(https://github.com/THUDM/ChatGLM3/blob/main/finetune_demo/configs/lora.yaml)
Hello thanks for your great work.
I am trying finetuning glm3 with lora, but I am a bit confused by the difference between
max_output_length
and themax_new_tokens
. I read the finetuning code and noticed onlymax_output_length
andmax_input_length
are used when cutting input data . So what doesmax_new_tokens
do ? Do I need to make sure it is larger than the longest turn of conversation in my data?say the data have many turns and the token number of each turn is like this:
so Does it mean, before I finetune the model, I need to make sure the
max_new_tokens
should be set greater than the longest assistant turn in my data(i.e. 123)?Is my understanding correct? Any clarification is greatly appreciated!!