AMD about baichuan-13b HOT 2 CLOSED

docker pull rocm/deepspeed:rocm5.7_ubuntu20.04_py3.9_pytorch_2.0.1_DeepSpeed
docker run -it --device /dev/kfd --device /dev/dri dfac3db401df /bin/bash

# 不要直接 pip install -r requirements.txt，那是 nvidia 版本的依赖
pip install numpy
pip install transformers
pip install sentencepiece
pip install tokenizers
pip install accelerate

# 安装 rocm 版 bitsandbytes
cd /home
git clone https://github.com/Lzy17/bitsandbytes-rocm
cd bitsandbytes-rocm
make hip
python setup.py install

cd /home
git clone https://github.com/baichuan-inc/Baichuan2.git
cd Baichuan2/fine-tune

# 显卡不支持 bf16 和 tf32
hostfile=""
deepspeed --hostfile=$hostfile fine-tune.py  \
    --report_to "none" \
    --data_path "data/belle_chat_ramdon_10k.json" \
    --model_name_or_path "baichuan-inc/Baichuan2-7B-Base" \
    --output_dir "output" \
    --model_max_length 512 \
    --num_train_epochs 4 \
    --per_device_train_batch_size 16 \
    --gradient_accumulation_steps 1 \
    --save_strategy epoch \
    --learning_rate 2e-5 \
    --lr_scheduler_type constant \
    --adam_beta1 0.9 \
    --adam_beta2 0.98 \
    --adam_epsilon 1e-8 \
    --max_grad_norm 1.0 \
    --weight_decay 1e-4 \
    --warmup_ratio 0.0 \
    --logging_steps 1 \
    --gradient_checkpointing True \
    --deepspeed ds_config.json \
    --fp16 True