CUDA_VISIBLE_DEVICES=0,1,2,3,5 torchrun --nproc_per_node 5 ../supervised_finetuning.py \
    --model_type auto \
    --model_name_or_path /data/llm/models/Pretrained/yi-6B/01ai/Yi-6B \
    --tokenizer_name_or_path /data/llm/models/Pretrained/yi-6B/01ai/Yi-6B \
    --train_file_dir ../data/finetune/vicuna/ \
    --per_device_train_batch_size 2\
    --do_train \
    --max_train_samples -1 \
    --num_train_epochs 3 \
    --learning_rate 2e-5 \
    --weight_decay 0. \
    --bf16 \
    --use_peft False \
    --logging_strategy steps \
    --logging_steps 10 \
    --save_strategy epoch \
    --save_total_limit 5 \
    --gradient_accumulation_steps 1 \
    --preprocessing_num_workers 8 \
    --output_dir ../outputs/20240106_yi6B_vicuna \
    --overwrite_output_dir \
    --ddp_timeout 30000 \
    --logging_first_step True \
    --torch_dtype bfloat16 \
    --device_map auto \
    --report_to tensorboard \
    --ddp_find_unused_parameters False \
    --gradient_checkpointing True \
    --cache_dir ./cache \
    --model_max_length 4096 \
    --deepspeed ../deepspeed_zero_stage2_config_no16.json \
    --template_name yi   

***** train metrics *****
  epoch                    =                3.0
  train_loss               =             0.3785
  train_runtime            = 1 day, 10:01:13.95
  train_samples            =              93204
  train_samples_per_second =               2.24
  train_steps_per_second   =              0.224

CUDA_VISIBLE_DEVICES=4 python gradio_demo.py  --model_type auto --base_model /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna    --tokenizer_path /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna --template_name yi --gpus 4
CUDA_VISIBLE_DEVICES=6 python inference.py --model_type auto --base_model /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna      --template_name yi --gpus 6     --interactive --tokenizer_path /data/llm/models/Pretrained/yi-6B/01ai/Yi-6B