环境

单卡 A100

代码[1]

dataset = load_dataset("./dataset/FreedomIntelligence/medical-o1-reasoning-SFT","en", split = "train",trust_remote_code=True)
dataset = dataset.map(formatting_prompts_func, batched = True,)
dataset["text"][0]

model = FastLanguageModel.get_peft_model(
    model,
    r=16,  
    target_modules=[
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj",
    ],
    lora_alpha=16,
    lora_dropout=0,  
    bias="none",  
    use_gradient_checkpointing="unsloth",  # True or "unsloth" for very long context
    random_state=3407,
    use_rslora=False,  
    loftq_config=None,
)

from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import is_bfloat16_supported

trainer = SFTTrainer(
    model=model,
    tokenizer=tokenizer,
    train_dataset=dataset,
    dataset_text_field="text",
    max_seq_length=max_seq_length,
    dataset_num_proc=2,
    args=TrainingArguments(
        per_device_train_batch_size=2,
        gradient_accumulation_steps=4,
        num_train_epochs = 1,   # 3 
        warmup_steps=5,
        # max_steps=60,
        learning_rate=2e-4,
        fp16=not is_bfloat16_supported(),
        bf16=is_bfloat16_supported(),
        logging_steps=10,
        optim="adamw_8bit",
        weight_decay=0.01,
        lr_scheduler_type="linear",
        seed=3407,
        output_dir="outputs",
    ),
)

trainer_stats = trainer.train()

1个epoch，运行2:03:46

DataSet

Paper

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

HuatuoGPT-o1 git

数据格式

FreedomIntelligence/medical-o1-reasoning-SFT modelscope