def main()

in trl/scripts/grpo.py [0:0]

• 42 lines of code
• 11 McCabe index (conditional complexity)

def main(script_args, training_args, model_args):
    # Load a pretrained model
    model = AutoModelForCausalLM.from_pretrained(
        model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
    )
    tokenizer = AutoTokenizer.from_pretrained(
        model_args.model_name_or_path, trust_remote_code=model_args.trust_remote_code
    )

    # Get the reward models and functions
    reward_funcs = []
    if script_args.reward_model_name_or_path:
        reward_model = AutoModelForSequenceClassification.from_pretrained(
            script_args.reward_model_name_or_path, trust_remote_code=model_args.trust_remote_code, num_labels=1
        )
        reward_funcs.append(reward_model)

    if script_args.reward_funcs:
        for func_name in script_args.reward_funcs:
            if func_name in reward_funcs_registry:
                reward_funcs.append(reward_funcs_registry[func_name])
            elif "." in func_name:
                module_path, func_name = func_name.rsplit(".", 1)
                sys.path.insert(0, os.getcwd())
                module = importlib.import_module(module_path)
                reward_func = getattr(module, func_name)
                reward_funcs.append(reward_func)
            else:
                raise ValueError(
                    f"Could not load reward function '{func_name}'. Expected one of "
                    f"{list(reward_funcs_registry.keys())} or a valid import path."
                )

    # Load the dataset
    dataset = load_dataset(script_args.dataset_name, name=script_args.dataset_config)

    # Initialize the GRPO trainer
    trainer = GRPOTrainer(
        model=model,
        reward_funcs=reward_funcs,
        args=training_args,
        train_dataset=dataset[script_args.dataset_train_split],
        eval_dataset=dataset[script_args.dataset_test_split] if training_args.eval_strategy != "no" else None,
        processing_class=tokenizer,
        peft_config=get_peft_config(model_args),
    )

    # Train and push the model to the Hub
    trainer.train()

    # Save and push to hub
    trainer.save_model(training_args.output_dir)
    if training_args.push_to_hub:
        trainer.push_to_hub(dataset_name=script_args.dataset_name)