2_slm-fine-tuning-mlstudio/phi/src_train/train.py [121:172]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    peft_conf = LoraConfig(**peft_config)
    model, tokenizer = load_model(args)

    ###############
    # 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 = train_conf.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: {train_conf.local_rank}, device: {train_conf.device}, n_gpu: {train_conf.n_gpu}"
        + f" distributed training: {bool(train_conf.local_rank != -1)}, 16-bits training: {train_conf.fp16}"
    )
    logger.info(f"Training/evaluation parameters {train_conf}")
    logger.info(f"PEFT parameters {peft_conf}")

    ##################
    # Data Processing
    ##################
    train_dataset = load_dataset(
        "json", data_files=os.path.join(args.train_dir, "train.jsonl"), split="train"
    )
    eval_dataset = load_dataset(
        "json", data_files=os.path.join(args.train_dir, "eval.jsonl"), split="train"
    )
    column_names = list(train_dataset.features)

    processed_train_dataset = train_dataset.map(
        apply_chat_template,
        fn_kwargs={"tokenizer": tokenizer},
        num_proc=10,
        remove_columns=column_names,
        desc="Applying chat template to train_sft",
    )

    processed_eval_dataset = eval_dataset.map(
        apply_chat_template,
        fn_kwargs={"tokenizer": tokenizer},
        num_proc=10,
        remove_columns=column_names,
        desc="Applying chat template to test_sft",
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



2_slm-fine-tuning-mlstudio/phi/src_train/train_mlflow.py [144:195]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    peft_conf = LoraConfig(**peft_config)
    model, tokenizer = load_model(args)

    ###############
    # 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 = train_conf.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: {train_conf.local_rank}, device: {train_conf.device}, n_gpu: {train_conf.n_gpu}"
        + f" distributed training: {bool(train_conf.local_rank != -1)}, 16-bits training: {train_conf.fp16}"
    )
    logger.info(f"Training/evaluation parameters {train_conf}")
    logger.info(f"PEFT parameters {peft_conf}")

    ##################
    # Data Processing
    ##################
    train_dataset = load_dataset(
        "json", data_files=os.path.join(args.train_dir, "train.jsonl"), split="train"
    )
    eval_dataset = load_dataset(
        "json", data_files=os.path.join(args.train_dir, "eval.jsonl"), split="train"
    )
    column_names = list(train_dataset.features)

    processed_train_dataset = train_dataset.map(
        apply_chat_template,
        fn_kwargs={"tokenizer": tokenizer},
        num_proc=10,
        remove_columns=column_names,
        desc="Applying chat template to train_sft",
    )

    processed_eval_dataset = eval_dataset.map(
        apply_chat_template,
        fn_kwargs={"tokenizer": tokenizer},
        num_proc=10,
        remove_columns=column_names,
        desc="Applying chat template to test_sft",
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -