CPM-Bee大模型微调

$ git clone -b main --single-branch https://github.com/OpenBMB/CPM-Bee.git

docker pull pytorch/pytorch:1.13.1-cuda11.6-cudnn8-devel

{"input": "昏暗的灯熄灭了又被重新点亮。", "options": {"<option_0>": "渔灯灭复明", "<option_1>": "残灯灭又然", "<option_2>": "残灯暗复明", "<option_3>": "残灯灭又明"}, "question": "这段话形容了哪句诗的意境？", "<ans>": "<option_3>"}

# 四卡微调
# export CUDA_VISIBLE_DEVICES=0,1,2,3
# GPUS_PER_NODE=4
# 单卡微调
export CUDA_VISIBLE_DEVICES=0
GPUS_PER_NODE=1
NNODES=1
MASTER_ADDR="localhost"
MASTER_PORT=12346
OPTS=""
OPTS+=" --use-delta"  # 使用增量微调（delta-tuning）
OPTS+=" --model-config config/cpm-bee-1b.json"  # 模型配置文件
OPTS+=" --dataset ../tutorials/basic_task_finetune/bin_data/train"  # 训练集路径
OPTS+=" --eval_dataset ../tutorials/basic_task_finetune/bin_data/eval"  # 验证集路径
OPTS+=" --epoch 5"  # 训练epoch数
OPTS+=" --batch-size 5"    # 数据批次大小
OPTS+=" --train-iters 100"  # 用于lr_schedular
OPTS+=" --save-name cpm_bee_finetune"  # 保存名称
OPTS+=" --max-length 2048" # 最大长度
OPTS+=" --save results/"  # 保存路径
OPTS+=" --lr 0.0001"    # 学习率
OPTS+=" --inspect-iters 100"  # 每100个step进行一次检查(bmtrain inspect)
OPTS+=" --warmup-iters 1". # 预热学习率的步数为1
OPTS+=" --eval-interval 50"  # 每50步验证一次
OPTS+=" --early-stop-patience 5"  # 如果验证集loss连续5次不降，停止微调
OPTS+=" --lr-decay-style noam"  # 选择noam方式调度学习率
OPTS+=" --weight-decay 0.01"  # 优化器权重衰减率为0.01
OPTS+=" --clip-grad 1.0"  # 半精度训练的grad clip
OPTS+=" --loss-scale 32768"  # 半精度训练的loss scale
OPTS+=" --start-step 0"  # 用于加载lr_schedular的中间状态
OPTS+=" --load ckpts/pytorch_model.bin"  # 模型参数文件
CMD="torchrun --nnodes=${NNODES} --nproc_per_node=${GPUS_PER_NODE} --rdzv_id=1 --rdzv_backend=c10d --rdzv_endpoint=${MASTER_ADDR}:${MASTER_PORT} finetune_cpm_bee.py ${OPTS}"
echo ${CMD}
$CMD

{
    "vocab_size": 86583,
    "dim_model": 4096,
    "dim_ff" : 1024,
    "num_layers" : 48,
    "num_heads": 32,
    "dim_head" : 40,
    "dropout_p" : 0.0,
    "position_bias_num_buckets" : 256,
    "position_bias_num_segment_buckets": 256,
    "position_bias_max_distance" : 2048,
    "eps" : 1e-6,
    "half" : true,
    "mask_modules": [[false, false], [true, false], [false, false], [true, false], [true, true], [true, false], [true, true], [true, true], [false, false], [false, false], [true, true], [true, false], [true, false], [true, true], [false, false], [true, true], [false, false], [false, true], [true, false], [true, true], [false, false], [false, true], [true, true], [true, true], [false, false], [true, true], [false, false], [true, true], [true, true], [false, false], [true, true], [false, false], [true, true], [false, false], [true, true], [true, false], [true, true], [true, true], [true, true], [false, false], [true, true], [false, false], [true, true], [true, true], [false, false], [true, true], [false, false], [false, false]]
}

$ cd ../../src
$ bash scripts/finetune_cpm_bee.sh

from cpm_live.generation.bee import CPMBeeBeamSearch
from cpm_live.models import CPMBeeTorch, CPMBeeConfig
from cpm_live.tokenizers import CPMBeeTokenizer
from opendelta import LoraModel
import torch
if __name__ == "__main__":
    data_list = [
    {"input": "昏暗的灯熄灭了又被重新点亮。", "options": {"<option_0>": "渔灯灭复明", "<option_1>": "残灯灭又然", "<option_2>": "残灯暗复明", "<option_3>": "残灯灭又明"}, "question": "这段话形容了哪句诗的意境？", "<ans>": ""},
{"input": "涤荡万里，威名远扬。", "options": {"<option_0>": "万里静氛埃", "<option_1>": "万里绝氛埃", "<option_2>": "万里绝风烟", "<option_3>": "万里绝妖氛"}, "question": "这段话形容了哪句诗的意境？", "<ans>": ""}
            ]
    config = CPMBeeConfig.from_json_file("config/cpm-bee-1b.json")
    ckpt_path = "ckpts/pytorch_model.bin"
    tokenizer = CPMBeeTokenizer()
    model = CPMBeeTorch(config=config)
    #insert LoRA if your model has been finetuned in delta-tuning.
    delta_model = LoraModel(backbone_model=model, modified_modules=["project_q", "project_v"], backend="hf")
    lora_ckpt_path = "results/cpm_bee_finetune-delta-best.pt"
    model.load_state_dict(torch.load(lora_ckpt_path), strict=False)
    model.load_state_dict(torch.load(ckpt_path), strict=False)
    model.cuda().eval()
    # use beam search
    beam_search = CPMBeeBeamSearch(
        model=model,
        tokenizer=tokenizer,
    )
    inference_results = beam_search.generate(data_list, max_length=100, repetition_penalty=1.1)
    for res in inference_results:
        print(res)