Supervised Learning（监督学习）

train.Config
├── model_name            which model to fine-tune
├── dataset_builder       SupervisedDatasetBuilder → SupervisedDataset
├── learning_rate          optimizer config (+ lr_schedule, adam_*)
├── evaluator_builders    what to measure during training
├── save_every / eval_every    checkpoint and eval cadence
└── lora_rank             LoRA adapter size

SupervisedDatasetBuilder
└── __call__() → (train_dataset, eval_dataset)
     │
     ▼
SupervisedDataset
├── get_batch(index) → list[tinker.Datum]
├── __len__() → number of batches
└── set_epoch(seed) → shuffle for next epoch

from tinker_cookbook.supervised import train

config = train.Config(
    log_path="~/logs/my-sft-run",
    model_name="Qwen/Qwen3-8B",
    dataset_builder=my_dataset_builder,
    learning_rate=1e-4,
    lora_rank=32,
    num_epochs=1,
    save_every=20,
    eval_every=10,
)
asyncio.run(train.main(config))

from tinker_cookbook.supervised.types import SupervisedDatasetBuilder, SupervisedDataset

class MyDatasetBuilder(SupervisedDatasetBuilder):
    def __call__(self) -> tuple[SupervisedDataset, SupervisedDataset | None]:
        return train_data, eval_data  # eval_data is optional

from tinker_cookbook.supervised.types import ChatDatasetBuilder, ChatDatasetBuilderCommonConfig

class MyChats(ChatDatasetBuilder):
    common_config = ChatDatasetBuilderCommonConfig(
        model_name_for_tokenizer="Qwen/Qwen3-8B",
        renderer_name="qwen3",
        batch_size=8,
        max_length=4096,
    )