in CodeXGLUE/Text-Code/NL-code-search-Adv/code/run.py [0:0]
def main():
parser = argparse.ArgumentParser()
## Required parameters
parser.add_argument("--train_data_file", default=None, type=str, required=True,
help="The input training data file (a text file).")
parser.add_argument("--output_dir", default=None, type=str, required=True,
help="The output directory where the model predictions and checkpoints will be written.")
## Other parameters
parser.add_argument("--eval_data_file", default=None, type=str,
help="An optional input evaluation data file to evaluate the perplexity on (a text file).")
parser.add_argument("--test_data_file", default=None, type=str,
help="An optional input evaluation data file to evaluate the perplexity on (a text file).")
parser.add_argument("--model_type", default="bert", type=str,
help="The model architecture to be fine-tuned.")
parser.add_argument("--model_name_or_path", default=None, type=str,
help="The model checkpoint for weights initialization.")
parser.add_argument("--mlm", action='store_true',
help="Train with masked-language modeling loss instead of language modeling.")
parser.add_argument("--mlm_probability", type=float, default=0.15,
help="Ratio of tokens to mask for masked language modeling loss")
parser.add_argument("--config_name", default="", type=str,
help="Optional pretrained config name or path if not the same as model_name_or_path")
parser.add_argument("--tokenizer_name", default="", type=str,
help="Optional pretrained tokenizer name or path if not the same as model_name_or_path")
parser.add_argument("--cache_dir", default="", type=str,
help="Optional directory to store the pre-trained models downloaded from s3 (instread of the default one)")
parser.add_argument("--block_size", default=-1, type=int,
help="Optional input sequence length after tokenization."
"The training dataset will be truncated in block of this size for training."
"Default to the model max input length for single sentence inputs (take into account special tokens).")
parser.add_argument("--do_train", action='store_true',
help="Whether to run training.")
parser.add_argument("--do_eval", action='store_true',
help="Whether to run eval on the dev set.")
parser.add_argument("--do_test", action='store_true',
help="Whether to run eval on the dev set.")
parser.add_argument("--evaluate_during_training", action='store_true',
help="Run evaluation during training at each logging step.")
parser.add_argument("--do_lower_case", action='store_true',
help="Set this flag if you are using an uncased model.")
parser.add_argument("--train_batch_size", default=4, type=int,
help="Batch size per GPU/CPU for training.")
parser.add_argument("--eval_batch_size", default=4, type=int,
help="Batch size per GPU/CPU for evaluation.")
parser.add_argument('--gradient_accumulation_steps', type=int, default=1,
help="Number of updates steps to accumulate before performing a backward/update pass.")
parser.add_argument("--learning_rate", default=5e-5, type=float,
help="The initial learning rate for Adam.")
parser.add_argument("--weight_decay", default=0.0, type=float,
help="Weight deay if we apply some.")
parser.add_argument("--adam_epsilon", default=1e-8, type=float,
help="Epsilon for Adam optimizer.")
parser.add_argument("--max_grad_norm", default=1.0, type=float,
help="Max gradient norm.")
parser.add_argument("--num_train_epochs", default=1.0, type=float,
help="Total number of training epochs to perform.")
parser.add_argument("--max_steps", default=-1, type=int,
help="If > 0: set total number of training steps to perform. Override num_train_epochs.")
parser.add_argument("--warmup_steps", default=0, type=int,
help="Linear warmup over warmup_steps.")
parser.add_argument('--logging_steps', type=int, default=50,
help="Log every X updates steps.")
parser.add_argument('--save_steps', type=int, default=50,
help="Save checkpoint every X updates steps.")
parser.add_argument('--save_total_limit', type=int, default=None,
help='Limit the total amount of checkpoints, delete the older checkpoints in the output_dir, does not delete by default')
parser.add_argument("--eval_all_checkpoints", action='store_true',
help="Evaluate all checkpoints starting with the same prefix as model_name_or_path ending and ending with step number")
parser.add_argument("--no_cuda", action='store_true',
help="Avoid using CUDA when available")
parser.add_argument('--overwrite_output_dir', action='store_true',
help="Overwrite the content of the output directory")
parser.add_argument('--overwrite_cache', action='store_true',
help="Overwrite the cached training and evaluation sets")
parser.add_argument('--seed', type=int, default=42,
help="random seed for initialization")
parser.add_argument('--epoch', type=int, default=42,
help="random seed for initialization")
parser.add_argument('--fp16', action='store_true',
help="Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit")
parser.add_argument('--fp16_opt_level', type=str, default='O1',
help="For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
"See details at https://nvidia.github.io/apex/amp.html")
parser.add_argument("--local_rank", type=int, default=-1,
help="For distributed training: local_rank")
parser.add_argument('--server_ip', type=str, default='', help="For distant debugging.")
parser.add_argument('--server_port', type=str, default='', help="For distant debugging.")
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)
config.num_labels=1
tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
do_lower_case=args.do_lower_case,
cache_dir=args.cache_dir if args.cache_dir else None)
if args.block_size <= 0:
args.block_size = tokenizer.max_len_single_sentence # Our input block size will be the max possible for the model
args.block_size = min(args.block_size, tokenizer.max_len_single_sentence)
if args.model_name_or_path:
model = model_class.from_pretrained(args.model_name_or_path,
from_tf=bool('.ckpt' in args.model_name_or_path),
config=config,
cache_dir=args.cache_dir if args.cache_dir else None)
else:
model = model_class(config)
model=Model(model,config,tokenizer,args)
if args.local_rank == 0:
torch.distributed.barrier() # End of barrier to make sure only the first process in distributed training download model & vocab
logger.info("Training/evaluation parameters %s", args)
# Training
if args.do_train:
if args.local_rank not in [-1, 0]:
torch.distributed.barrier() # Barrier to make sure only the first process in distributed training process the dataset, and the others will use the cache
train_dataset = TextDataset(tokenizer, args,args.train_data_file)
if args.local_rank == 0:
torch.distributed.barrier()
train(args, train_dataset, model, tokenizer)
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
checkpoint_prefix = 'checkpoint-best-mrr/model.bin'
output_dir = os.path.join(args.output_dir, '{}'.format(checkpoint_prefix))
model.load_state_dict(torch.load(output_dir))
model.to(args.device)
result=evaluate(args, model, tokenizer)
logger.info("***** Eval results *****")
for key in sorted(result.keys()):
logger.info(" %s = %s", key, str(round(result[key],4)))
if args.do_test and args.local_rank in [-1, 0]:
checkpoint_prefix = 'checkpoint-best-mrr/model.bin'
output_dir = os.path.join(args.output_dir, '{}'.format(checkpoint_prefix))
model.load_state_dict(torch.load(output_dir))
model.to(args.device)
test(args, model, tokenizer)
return results