flower-kyo

/home/ma-user/anaconda3/envs/chatglmeV2/bin/python /home/ma-user/work/zhanghongjun/ChatGLM-Efficient-Tuning-main/src/train_ppo.py --do_train --dataset alpaca_gpt4_en --finetuning_type lora --checkpoint_dir path_to_sft_checkpoint --reward_model path_to_rm_checkpoint --output_dir path_to_ppo_checkpoint --per_device_train_batch_size 2 --gradient_accumulation_steps 4 --lr_scheduler_type cosine --logging_steps 10 --save_steps 1000 --learning_rate 1e-5 --num_train_epochs 1.0 --fp16 /home/ma-user/anaconda3/envs/chatglmeV2/lib/python3.7/site-packages/requests/__init__.py:104: RequestsDependencyWarning:...