def main()

in src/open_r1/grpo.py [0:0]

• 87 lines of code
• 19 McCabe index (conditional complexity)

def main(script_args, training_args, model_args):
    # Set seed for reproducibility
    set_seed(training_args.seed)

    ###############
    # Setup logging
    ###############
    logging.basicConfig(
        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
        datefmt="%Y-%m-%d %H:%M:%S",
        handlers=[logging.StreamHandler(sys.stdout)],
    )
    log_level = training_args.get_process_log_level()
    logger.setLevel(log_level)
    datasets.utils.logging.set_verbosity(log_level)
    transformers.utils.logging.set_verbosity(log_level)
    transformers.utils.logging.enable_default_handler()
    transformers.utils.logging.enable_explicit_format()

    # Log on each process a small summary
    logger.warning(
        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
        + f" distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
    )
    logger.info(f"Model parameters {model_args}")
    logger.info(f"Script parameters {script_args}")
    logger.info(f"Training parameters {training_args}")

    # Check for last checkpoint
    last_checkpoint = None
    if os.path.isdir(training_args.output_dir):
        last_checkpoint = get_last_checkpoint(training_args.output_dir)
    if last_checkpoint is not None and training_args.resume_from_checkpoint is None:
        logger.info(f"Checkpoint detected, resuming training at {last_checkpoint=}.")

    if "wandb" in training_args.report_to:
        init_wandb_training(training_args)

    # Load the dataset
    dataset = get_dataset(script_args)

    ################
    # Load tokenizer
    ################
    tokenizer = get_tokenizer(model_args, training_args)

    ##############
    # Load model #
    ##############
    logger.info("*** Loading model ***")
    model = get_model(model_args, training_args)

    # Get reward functions from the registry
    reward_funcs = get_reward_funcs(script_args)

    # Format into conversation
    def make_conversation(example, prompt_column: str = script_args.dataset_prompt_column):
        prompt = []

        if training_args.system_prompt is not None:
            prompt.append({"role": "system", "content": training_args.system_prompt})

        if prompt_column not in example:
            raise ValueError(f"Dataset Question Field Error: {prompt_column} is not supported.")

        prompt.append({"role": "user", "content": example[prompt_column]})
        return {"prompt": prompt}

    dataset = dataset.map(make_conversation)

    for split in dataset:
        if "messages" in dataset[split].column_names:
            dataset[split] = dataset[split].remove_columns("messages")

    #############################
    # 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),
        peft_config=get_peft_config(model_args),
        callbacks=get_callbacks(training_args, model_args),
        processing_class=tokenizer,
    )

    ###############
    # Training loop
    ###############
    logger.info("*** Train ***")
    checkpoint = None
    if training_args.resume_from_checkpoint is not None:
        checkpoint = training_args.resume_from_checkpoint
    elif last_checkpoint is not None:
        checkpoint = last_checkpoint
    train_result = trainer.train(resume_from_checkpoint=checkpoint)
    metrics = train_result.metrics
    metrics["train_samples"] = len(dataset[script_args.dataset_train_split])
    trainer.log_metrics("train", metrics)
    trainer.save_metrics("train", metrics)
    trainer.save_state()

    ##################################
    # Save model and create model card
    ##################################
    logger.info("*** Save model ***")
    # Align the model's generation config with the tokenizer's eos token
    # to avoid unbounded generation in the transformers `pipeline()` function
    trainer.model.generation_config.eos_token_id = tokenizer.eos_token_id
    trainer.save_model(training_args.output_dir)
    logger.info(f"Model saved to {training_args.output_dir}")

    # Save everything else on main process
    kwargs = {
        "dataset_name": script_args.dataset_name,
        "tags": ["open-r1"],
    }
    if trainer.accelerator.is_main_process:
        trainer.create_model_card(**kwargs)
        # Restore k,v cache for fast inference
        trainer.model.config.use_cache = True
        trainer.model.config.save_pretrained(training_args.output_dir)

    ##########
    # Evaluate
    ##########
    if training_args.do_eval:
        logger.info("*** Evaluate ***")
        metrics = trainer.evaluate()
        metrics["eval_samples"] = len(dataset[script_args.dataset_test_split])
        trainer.log_metrics("eval", metrics)
        trainer.save_metrics("eval", metrics)

    #############
    # push to hub
    #############
    if training_args.push_to_hub:
        logger.info("Pushing to hub...")
        trainer.push_to_hub(**kwargs)