【书生大模型实战营】InternLM 论文分类微调实践（XTuner 版） 中等

# Copyright (c) OpenMMLab. All rights reserved.
# —— 动态补丁：兼容 transformers>=4.48 ——
from transformers.cache_utils import DynamicCache     # 1. 引入类
if not hasattr(DynamicCache, "get_max_length"):       # 2. 判断是否缺失
    DynamicCache.get_max_length = DynamicCache.get_max_cache_shape  # 3. 补一个别名
import torch
from datasets import load_dataset
from mmengine.dataset import DefaultSampler
from mmengine.hooks import (
    CheckpointHook,
    DistSamplerSeedHook,
    IterTimerHook,
    LoggerHook,
    ParamSchedulerHook,
)
from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR
from peft import LoraConfig
from torch.optim import AdamW
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

from xtuner.dataset import process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import alpaca_map_fn, template_map_fn_factory
from xtuner.engine.hooks import (
    DatasetInfoHook,
    EvaluateChatHook,
    VarlenAttnArgsToMessageHubHook,
)
from xtuner.engine.runner import TrainLoop
from xtuner.model import SupervisedFinetune
from xtuner.parallel.sequence import SequenceParallelSampler
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = "./internlm2_5-7b-chat"
use_varlen_attn = False

# Data
alpaca_en_path = "/root/L1G4/sftdata.jsonl"#换成自己的数据路径
prompt_template = PROMPT_TEMPLATE.internlm2_chat
max_length = 1024
pack_to_max_length = True

# parallel
sequence_parallel_size = 1

# Scheduler & Optimizer
batch_size = 2  # per_device
accumulative_counts = 1
accumulative_counts *= sequence_parallel_size
dataloader_num_workers = 0
max_epochs = 1
optim_type = AdamW
lr = 2e-4
betas = (0.9, 0.999)
weight_decay = 0
max_norm = 1  # grad clip
warmup_ratio = 0.03

# Save
save_steps = 50
save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 50
SYSTEM = SYSTEM_TEMPLATE.alpaca
evaluation_inputs = ["请给我介绍五个上海的景点", "Please tell me five scenic spots in Shanghai"]

#######################################################################
#                      PART 2  Model & Tokenizer                      #
#######################################################################
tokenizer = dict(
    type=AutoTokenizer.from_pretrained,
    pretrained_model_name_or_path=pretrained_model_name_or_path,
    trust_remote_code=True,
    padding_side="right",
)

model = dict(
    type=SupervisedFinetune,
    use_varlen_attn=use_varlen_attn,
    llm=dict(
        type=AutoModelForCausalLM.from_pretrained,
        pretrained_model_name_or_path=pretrained_model_name_or_path,
        trust_remote_code=True,
        torch_dtype=torch.float16,
        quantization_config=dict(
            type=BitsAndBytesConfig,
            load_in_4bit=True,
            load_in_8bit=False,
            llm_int8_threshold=6.0,
            llm_int8_has_fp16_weight=False,
            bnb_4bit_compute_dtype=torch.float16,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type="nf4",
        ),
    ),
    lora=dict(
        type=LoraConfig,
        r=64,
        lora_alpha=16,
        lora_dropout=0.1,
        bias="none",
        task_type="CAUSAL_LM",
    ),
)

#######################################################################
#                      PART 3  Dataset & Dataloader                   #
#######################################################################
alpaca_en = dict(
    type=process_hf_dataset,
    dataset=dict(type=load_dataset, path='json', data_files=alpaca_en_path),
    tokenizer=tokenizer,
    max_length=max_length,
    dataset_map_fn=alpaca_map_fn,
    template_map_fn=dict(type=template_map_fn_factory, template=prompt_template),
    remove_unused_columns=True,
    shuffle_before_pack=True,
    pack_to_max_length=pack_to_max_length,
    use_varlen_attn=use_varlen_attn,
)

sampler = SequenceParallelSampler if sequence_parallel_size > 1 else DefaultSampler
train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=alpaca_en,
    sampler=dict(type=sampler, shuffle=True),
    collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn),
)

#######################################################################
#                    PART 4  Scheduler & Optimizer                    #
#######################################################################
# optimizer
optim_wrapper = dict(
    type=AmpOptimWrapper,
    optimizer=dict(type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay),
    clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False),
    accumulative_counts=accumulative_counts,
    loss_scale="dynamic",
    dtype="float16",
)

# learning policy
# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md  # noqa: E501
param_scheduler = [
    dict(
        type=LinearLR,
        start_factor=1e-5,
        by_epoch=True,
        begin=0,
        end=warmup_ratio * max_epochs,
        convert_to_iter_based=True,
    ),
    dict(
        type=CosineAnnealingLR,
        eta_min=0.0,
        by_epoch=True,
        begin=warmup_ratio * max_epochs,
        end=max_epochs,
        convert_to_iter_based=True,
    ),
]

# train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)

#######################################################################
#                           PART 5  Runtime                           #
#######################################################################
# Log the dialogue periodically during the training process, optional
custom_hooks = [
    dict(type=DatasetInfoHook, tokenizer=tokenizer),
    dict(
        type=EvaluateChatHook,
        tokenizer=tokenizer,
        every_n_iters=evaluation_freq,
        evaluation_inputs=evaluation_inputs,
        system=SYSTEM,
        prompt_template=prompt_template,
    ),
]

if use_varlen_attn:
    custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]

# configure default hooks
default_hooks = dict(
    # record the time of every iteration.
    timer=dict(type=IterTimerHook),
    # print log every 10 iterations.
    logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
    # enable the parameter scheduler.
    param_scheduler=dict(type=ParamSchedulerHook),
    # save checkpoint per `save_steps`.
    checkpoint=dict(
        type=CheckpointHook,
        by_epoch=False,
        interval=save_steps,
        max_keep_ckpts=save_total_limit,
    ),
    # set sampler seed in distributed evrionment.
    sampler_seed=dict(type=DistSamplerSeedHook),
)

# configure environment
env_cfg = dict(
    # whether to enable cudnn benchmark
    cudnn_benchmark=False,
    # set multi process parameters
    mp_cfg=dict(mp_start_method="fork", opencv_num_threads=0),
    # set distributed parameters
    dist_cfg=dict(backend="nccl"),
)

# set visualizer
visualizer = None

# set log level
log_level = "INFO"

# load from which checkpoint
load_from = None

# whether to resume training from the loaded checkpoint
resume = False

# Defaults to use random seed and disable `deterministic`
randomness = dict(seed=None, deterministic=False)

# set log processor
log_processor = dict(by_epoch=False)

from modelscope.hub.api import HubApi
from modelscope.hub.constants import Licenses, ModelVisibility

# 配置基本信息
YOUR_ACCESS_TOKEN = 'xxx(从modelscope获取，即上节的hub_token)'
api = HubApi()
api.login(YOUR_ACCESS_TOKEN)

# 取名字
owner_name = 'xxx'    # ModelScope 的用户名，需根据自己情况修改
model_name = 'xxx'    # 为模型库取个响亮优雅又好听的名字，需根据自己情况修改
model_id = f"{owner_name}/{model_name}"

# 创建模型库，若已通过6.1节的ModelScope网页端创建，此段代码可忽略
api.create_model(
     model_id,
     visibility=ModelVisibility.PUBLIC,
     license=Licenses.APACHE_V2,
     chinese_name=f"{owner_name}的论文分类打榜赛模型"
    )

# 上传模型
api.upload_folder(
    repo_id=f"{owner_name}/{model_name}",
    folder_path='/root/path/to/your/model',    # 微调后模型的文件夹名称
    commit_message='upload model folder to repo',    # 写点开心的上传信息
)