You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Do smaller batch_size help? I see you using batch size 4. I'm doing full parameter finetuning with badam so I think you should be able to do eval by lower the batch_size...
Do smaller batch_size help? I see you using batch size 4. I'm doing full parameter finetuning with badam so I think you should be able to do eval by lower the batch_size...
Reminder
Reproduction
CUDA_VISIBLE_DEVICES=0 USE_MODELSCOPE_HUB=1 python src/evaluate.py --model_name_or_path LLM-Research/Meta-Llama-3-8B-Instruct --template llama3 --finetuning_type lora --task ceval --split validation --lang zh --n_shot 5 --batch_size 4
Expected behavior
我希望在
/LLaMA-Factory/src/llmtuner/eval/evaluator.py
def eval(self) -> None: 函数下添加我在评测循环尾部添加了显存释放模块,我的操作是合法的吗? 有不利的地方吗? 它至少能让我在单卡24G上做评测
System Info
No response
Others
我还不会做github 代码提交,所以暂时以提问形式作补充:
if 我的操作有什么更优的方式,希望能分享一下
The text was updated successfully, but these errors were encountered: