CodeXGLUE/Code-Code/Clone-detection-BigCloneBench/code/run.py [532:587]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - args = parser.parse_args() # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script import ptvsd print("Waiting for debugger attach") ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) ptvsd.wait_for_attach() # Setup CUDA, GPU & distributed training 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") args.n_gpu = torch.cuda.device_count() else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs torch.cuda.set_device(args.local_rank) device = torch.device("cuda", args.local_rank) torch.distributed.init_process_group(backend='nccl') args.n_gpu = 1 args.device = device args.per_gpu_train_batch_size=args.train_batch_size//args.n_gpu args.per_gpu_eval_batch_size=args.eval_batch_size//args.n_gpu # Setup logging logging.basicConfig(format='%(asctime)s - %(levelname)s - %(name)s - %(message)s', datefmt='%m/%d/%Y %H:%M:%S', level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN) logger.warning("Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16) # Set seed set_seed(args.seed) # Load pretrained model and tokenizer if args.local_rank not in [-1, 0]: torch.distributed.barrier() # Barrier to make sure only the first process in distributed training download model & vocab args.start_epoch = 0 args.start_step = 0 checkpoint_last = os.path.join(args.output_dir, 'checkpoint-last') if os.path.exists(checkpoint_last) and os.listdir(checkpoint_last): args.model_name_or_path = os.path.join(checkpoint_last, 'pytorch_model.bin') args.config_name = os.path.join(checkpoint_last, 'config.json') idx_file = os.path.join(checkpoint_last, 'idx_file.txt') with open(idx_file, encoding='utf-8') as idxf: args.start_epoch = int(idxf.readlines()[0].strip()) + 1 step_file = os.path.join(checkpoint_last, 'step_file.txt') if os.path.exists(step_file): with open(step_file, encoding='utf-8') as stepf: args.start_step = int(stepf.readlines()[0].strip()) logger.info("reload model from {}, resume from {} epoch".format(checkpoint_last, args.start_epoch)) config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path, cache_dir=args.cache_dir if args.cache_dir else None) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - CodeXGLUE/Text-Code/NL-code-search-Adv/code/run.py [511:569]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - args = parser.parse_args() # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script import ptvsd print("Waiting for debugger attach") ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) ptvsd.wait_for_attach() # Setup CUDA, GPU & distributed training 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") args.n_gpu = torch.cuda.device_count() else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs torch.cuda.set_device(args.local_rank) device = torch.device("cuda", args.local_rank) torch.distributed.init_process_group(backend='nccl') args.n_gpu = 1 args.device = device args.per_gpu_train_batch_size=args.train_batch_size//args.n_gpu args.per_gpu_eval_batch_size=args.eval_batch_size//args.n_gpu # Setup logging logging.basicConfig(format='%(asctime)s - %(levelname)s - %(name)s - %(message)s', datefmt='%m/%d/%Y %H:%M:%S', level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN) logger.warning("Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16) # Set seed set_seed(args.seed) # Load pretrained model and tokenizer if args.local_rank not in [-1, 0]: torch.distributed.barrier() # Barrier to make sure only the first process in distributed training download model & vocab args.start_epoch = 0 args.start_step = 0 checkpoint_last = os.path.join(args.output_dir, 'checkpoint-last') if os.path.exists(checkpoint_last) and os.listdir(checkpoint_last): args.model_name_or_path = os.path.join(checkpoint_last, 'pytorch_model.bin') args.config_name = os.path.join(checkpoint_last, 'config.json') idx_file = os.path.join(checkpoint_last, 'idx_file.txt') with open(idx_file, encoding='utf-8') as idxf: args.start_epoch = int(idxf.readlines()[0].strip()) + 1 step_file = os.path.join(checkpoint_last, 'step_file.txt') if os.path.exists(step_file): with open(step_file, encoding='utf-8') as stepf: args.start_step = int(stepf.readlines()[0].strip()) logger.info("reload model from {}, resume from {} epoch".format(checkpoint_last, args.start_epoch)) config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type] config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path, cache_dir=args.cache_dir if args.cache_dir else None) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -