跳至主要内容

pb.adapters.create

pb.adapters.create

     通过启动一个新的（阻塞式）微调任务来创建一个新的适配器

参数:​

       config: FinetuningConfig, 默认 None

       dataset: str, default None
       用于微调的数据集

       continue_from_version: str, default None
       从中继续训练的适配器版本

       repo: str, default None
       用于存储新创建适配器的适配器仓库名称

       描述: str, 默认 None
       适配器的描述

       show_tensorboard: bool, 默认值 False
       如果为true，则启动一个tensorboard实例来查看训练日志

返回:​

       适配器

示例:​

示例1：使用默认设置创建适配器

# Create an adapter repository
repo = pb.repos.create(name="news-summarizer-model", description="TLDR News Summarizer Experiments", exists_ok=True)

# Start a fine-tuning job, blocks until training is finished
adapter = pb.adapters.create(
    config=FinetuningConfig(
        base_model="mistral-7b"
    ),
    dataset="tldr_news",
    repo=repo,
    description="initial model with defaults"
)

示例2：使用自定义参数创建新的适配器

# Create an adapter repository
repo = pb.repos.create(name="news-summarizer-model", description="TLDR News Summarizer Experiments", exists_ok=True)

# Start a fine-tuning job with custom parameters, blocks until training is finished
adapter = pb.adapters.create(
    config=FinetuningConfig(
        base_model="mistral-7b",
        task="instruction_tuning",
        epochs=1, # default: 3
        rank=8, # default: 16
        learning_rate=0.0001, # default: 0.0002
        target_modules=["q_proj", "v_proj", "k_proj"], # default: None (infers [q_proj, v_proj] for mistral-7b)
    ),
    dataset="tldr_news",
    repo=repo,
    description="changing epochs, rank, and learning rate"
)

示例3：在现有适配器版本的基础上继续训练以创建新适配器

adapter = pb.adapters.create(
    # Note: only `epochs` and `enable_early_stopping` are available parameters in this case.
    config=FinetuningConfig(
        epochs=3,  # The maximum number of ADDITIONAL epochs to train for
        enable_early_stopping=False,
    ),
    continue_from_version="myrepo/3",  # The adapter version to resume training from
    dataset="mydataset",
    repo="myrepo"
)

示例4：通过在现有适配器版本的特定检查点上继续训练来创建新适配器

adapter = pb.adapters.create(
    # Note: only `epochs` and `enable_early_stopping` are available parameters in this case.
    config=FinetuningConfig(
        epochs=3,  # The maximum number of ADDITIONAL epochs to train for
        enable_early_stopping=False,
    ),
    continue_from_version="myrepo/3@11",  # Resumes from checkpoint 11 of `myrepo/3`.
    dataset="mydataset",
    repo="myrepo"
)

异步微调任务​

pb.finetuning.jobs.create

     启动一个非阻塞的微调任务

参数:​

       config: FinetuningConfig, 默认 None

       dataset: str, default None
       用于微调的数据集

       repo: str, default None
       用于存储新创建适配器的适配器仓库名称

       描述: str, 默认 None
       适配器的描述

       watch: boolean, default False
       定义是否阻塞直到微调任务完成

返回:​

       微调任务

adapter: FinetuningJob = pb.finetuning.jobs.create(
    config=FinetuningConfig(
        base_model="mistral-7b",
        task="instruction_tuning",
        epochs=1, # default: 3
        rank=8, # default: 16
        learning_rate=0.0001 # default: 0.0002
        target_modules=["q_proj", "v_proj", "k_proj"], # default: None (infers [q_proj, v_proj] for mistral-7b)
    ),
    dataset=dataset,
    repo=repo,
    description="changing epochs, rank, and learning rate",
    watch=False,
)