CodeXGLUE/Code-Code/Clone-detection-BigCloneBench/code/run.py [208:246]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                                num_training_steps=args.max_steps)
    if args.fp16:
        try:
            from apex import amp
        except ImportError:
            raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.")
        model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level)

    # multi-gpu training (should be after apex fp16 initialization)
    if args.n_gpu > 1:
        model = torch.nn.DataParallel(model)

    # Distributed training (should be after apex fp16 initialization)
    if args.local_rank != -1:
        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank],
                                                          output_device=args.local_rank,
                                                          find_unused_parameters=True)

    checkpoint_last = os.path.join(args.output_dir, 'checkpoint-last')
    scheduler_last = os.path.join(checkpoint_last, 'scheduler.pt')
    optimizer_last = os.path.join(checkpoint_last, 'optimizer.pt')
    if os.path.exists(scheduler_last):
        scheduler.load_state_dict(torch.load(scheduler_last))
    if os.path.exists(optimizer_last):
        optimizer.load_state_dict(torch.load(optimizer_last))
    # Train!
    logger.info("***** Running training *****")
    logger.info("  Num examples = %d", len(train_dataset))
    logger.info("  Num Epochs = %d", args.num_train_epochs)
    logger.info("  Instantaneous batch size per GPU = %d", args.per_gpu_train_batch_size)
    logger.info("  Total train batch size (w. parallel, distributed & accumulation) = %d",
                args.train_batch_size * args.gradient_accumulation_steps * (
                    torch.distributed.get_world_size() if args.local_rank != -1 else 1))
    logger.info("  Gradient Accumulation steps = %d", args.gradient_accumulation_steps)
    logger.info("  Total optimization steps = %d", args.max_steps)

    global_step = args.start_step
    tr_loss, logging_loss,avg_loss,tr_nb,tr_num,train_loss = 0.0, 0.0,0.0,0,0,0
    best_mrr=0.0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



CodeXGLUE/Text-Code/NL-code-search-Adv/code/run.py [182:220]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                                num_training_steps=args.max_steps)
    if args.fp16:
        try:
            from apex import amp
        except ImportError:
            raise ImportError("Please install apex from https://www.github.com/nvidia/apex to use fp16 training.")
        model, optimizer = amp.initialize(model, optimizer, opt_level=args.fp16_opt_level)

    # multi-gpu training (should be after apex fp16 initialization)
    if args.n_gpu > 1:
        model = torch.nn.DataParallel(model)

    # Distributed training (should be after apex fp16 initialization)
    if args.local_rank != -1:
        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank],
                                                          output_device=args.local_rank,
                                                          find_unused_parameters=True)

    checkpoint_last = os.path.join(args.output_dir, 'checkpoint-last')
    scheduler_last = os.path.join(checkpoint_last, 'scheduler.pt')
    optimizer_last = os.path.join(checkpoint_last, 'optimizer.pt')
    if os.path.exists(scheduler_last):
        scheduler.load_state_dict(torch.load(scheduler_last))
    if os.path.exists(optimizer_last):
        optimizer.load_state_dict(torch.load(optimizer_last))
    # Train!
    logger.info("***** Running training *****")
    logger.info("  Num examples = %d", len(train_dataset))
    logger.info("  Num Epochs = %d", args.num_train_epochs)
    logger.info("  Instantaneous batch size per GPU = %d", args.per_gpu_train_batch_size)
    logger.info("  Total train batch size (w. parallel, distributed & accumulation) = %d",
                args.train_batch_size * args.gradient_accumulation_steps * (
                    torch.distributed.get_world_size() if args.local_rank != -1 else 1))
    logger.info("  Gradient Accumulation steps = %d", args.gradient_accumulation_steps)
    logger.info("  Total optimization steps = %d", args.max_steps)
    
    global_step = args.start_step
    tr_loss, logging_loss,avg_loss,tr_nb,tr_num,train_loss = 0.0, 0.0,0.0,0,0,0
    best_mrr=0.0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -