src/open_r1/grpo.py [121:178]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )

    ###############
    # 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)


if __name__ == "__main__":
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/open_r1/sft.py [109:166]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )

    ###############
    # 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)


if __name__ == "__main__":
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -