mdr/qa/train_ranker.py [44:84]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    args.output_dir = os.path.join(args.output_dir, date_curr, model_name)
    tb_logger = SummaryWriter(os.path.join(args.output_dir.replace("logs","tflogs")))

    if os.path.exists(args.output_dir) and os.listdir(args.output_dir):
        print(
            f"output directory {args.output_dir} already exists and is not empty.")
    if not os.path.exists(args.output_dir):
        os.makedirs(args.output_dir, exist_ok=True)

    logging.basicConfig(format='%(asctime)s - %(levelname)s - %(name)s - %(message)s', datefmt='%m/%d/%Y %H:%M:%S',
                        level=logging.INFO,
                        handlers=[logging.FileHandler(os.path.join(args.output_dir, "log.txt")),
                                  logging.StreamHandler()])
    logger = logging.getLogger(__name__)
    logger.info(args)

    if args.local_rank == -1 or args.no_cuda:
        device = torch.device(
            "cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu")
        n_gpu = torch.cuda.device_count()
    else:
        device = torch.device("cuda", args.local_rank)
        n_gpu = 1
        # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
        torch.distributed.init_process_group(backend='nccl')
    logger.info("device %s n_gpu %d distributed training %r",
                device, n_gpu, bool(args.local_rank != -1))

    if args.accumulate_gradients < 1:
        raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format(
            args.accumulate_gradients))

    args.train_batch_size = int(
        args.train_batch_size / args.accumulate_gradients)
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    if n_gpu > 0:
        torch.cuda.manual_seed_all(args.seed)

    bert_config = AutoConfig.from_pretrained(args.model_name)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



scripts/train_momentum.py [35:74]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    args.output_dir = os.path.join(args.output_dir, date_curr, model_name)
    tb_logger = SummaryWriter(os.path.join(args.output_dir.replace("logs","tflogs")))

    if os.path.exists(args.output_dir) and os.listdir(args.output_dir):
        print(
            f"output directory {args.output_dir} already exists and is not empty.")
    if not os.path.exists(args.output_dir):
        os.makedirs(args.output_dir, exist_ok=True)

    logging.basicConfig(format='%(asctime)s - %(levelname)s - %(name)s - %(message)s', datefmt='%m/%d/%Y %H:%M:%S',
                        level=logging.INFO,
                        handlers=[logging.FileHandler(os.path.join(args.output_dir, "log.txt")),
                                  logging.StreamHandler()])
    logger = logging.getLogger(__name__)
    logger.info(args)

    if args.local_rank == -1 or args.no_cuda:
        device = torch.device(
            "cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu")
        n_gpu = torch.cuda.device_count()
    else:
        device = torch.device("cuda", args.local_rank)
        n_gpu = 1
        torch.distributed.init_process_group(backend='nccl')
    logger.info("device %s n_gpu %d distributed training %r",
                device, n_gpu, bool(args.local_rank != -1))

    if args.accumulate_gradients < 1:
        raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format(
            args.accumulate_gradients))

    args.train_batch_size = int(
        args.train_batch_size / args.accumulate_gradients)
    random.seed(args.seed)
    np.random.seed(args.seed)
    torch.manual_seed(args.seed)
    if n_gpu > 0:
        torch.cuda.manual_seed_all(args.seed)

    bert_config = AutoConfig.from_pretrained(args.model_name)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -