Function main

train/train.py:221–451

()

def main():

    parser = transformers.HfArgumentParser(
        (ModelArguments, DataArguments, TrainingArguments, LoraArguments)
    )

    (
        model_args,
        data_args,
        training_args,
        lora_args,
    ) = parser.parse_args_into_dataclasses()
    
    device_map = "auto"
    world_size = int(os.environ.get("WORLD_SIZE", 1))
    ddp = world_size != 1
    if lora_args.use_q_lora:
        device_map = {"": int(os.environ.get("LOCAL_RANK") or 0)} if ddp else None
        if len(training_args.fsdp) > 0 or deepspeed.is_deepspeed_zero3_enabled():
            logging.warning(
                "FSDP or ZeRO3 are not incompatible with QLoRA."
            )

    send_example_telemetry("run_pt", model_args, data_args)

    # Setup logging
    logging.basicConfig(format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",datefmt="%m/%d/%Y %H:%M:%S",
        level=logging.INFO,  # if training_args.local_rank in [-1, 0] else logging.WARN,
        handlers=[logging.StreamHandler(sys.stdout)],)


    if training_args.should_log:
        # The default of training_args.log_level is passive, so we set log level at info here to have that default.
        transformers.utils.logging.set_verbosity_info()

    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 the 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 or training_args.bf16}"
    )

    # Detecting last checkpoint.
    last_checkpoint = None
    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
        last_checkpoint = get_last_checkpoint(training_args.output_dir)
        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
            raise ValueError(
                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
                "Use --overwrite_output_dir to overcome."
            )
        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None: