in BERT/main.py [0:0]
def main():
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument(
"--output_dir",
type=str,
required=True,
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--train_dir",
type=str,
required=True,
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--eval_dir",
type=str,
required=True,
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--test_dir",
type=str,
required=True,
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--vocab_file",
type=str,
required=True,
help="The vocab file.",
)
parser.add_argument(
"--event_type",
type=str,
required=True,
help="The event type.",
choices=['magenta', 'newevent']
)
parser.add_argument(
"--model_type", type=str, required=True, help="The model architecture to be trained or fine-tuned.",
)
parser.add_argument("--num_hidden_layers", default=5, type=int, help="Number of layers in BERT.")
parser.add_argument("--hidden_size", default=768, type=int, help="The number of hidden space")
### other parameters
parser.add_argument(
"--should_continue", action="store_true", help="Whether to continue from latest checkpoint in output_dir"
)
parser.add_argument(
"--model_name_or_path",
default=None,
type=str,
help="The model checkpoint for weights initialization. Leave None if you want to train a model from scratch.",
)
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=None,
type=str,
help="Optional pretrained config name or path if not the same as model_name_or_path. If both are None, "
"initialize a new config.",
)
parser.add_argument(
"--tokenizer_name",
default=None,
type=str,
help="Optional pretrained tokenizer name or path if not the same as model_name_or_path. If both are None, "
"initialize a new tokenizer.",
)
parser.add_argument(
"--cache_dir",
default=None,
type=str,
help="Optional directory to store the pre-trained models downloaded (instead 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(
"--evaluate_during_training", action="store_true", help="Run evaluation during training at each logging step."
)
parser.add_argument("--per_gpu_train_batch_size", default=2048, type=int,
help="Batch size per GPU/CPU for training.")
parser.add_argument(
"--per_gpu_eval_batch_size", default=2048, 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=1e-4, type=float, help="The initial learning rate for Adam.")
parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight decay 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=100000.0, 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=1000, type=int, help="Linear warmup over warmup_steps.")
parser.add_argument("--logging_steps", type=int, default=5000, help="Log every X updates steps.")
parser.add_argument("--save_steps", type=int, default=1000, help="Save checkpoint every X updates steps.")
parser.add_argument(
"--save_total_limit",
type=int,
default=20,
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(
"--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")
args = parser.parse_args()
if args.should_continue:
sorted_checkpoints = _sorted_checkpoints(args)
if len(sorted_checkpoints) == 0:
raise ValueError("Used --should_continue but no checkpoint was found in --output_dir.")
else:
args.model_name_or_path = sorted_checkpoints[-1]
if (
os.path.exists(args.output_dir)
and os.listdir(args.output_dir)
and args.do_train
and not args.overwrite_output_dir
):
raise ValueError(
"Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome.".format(
args.output_dir
)
)
# 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 = 0 if args.no_cuda else 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
# 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)
# 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
config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
if args.config_name:
config = config_class.from_pretrained(args.config_name, cache_dir=args.cache_dir)
elif args.model_name_or_path:
config = config_class.from_pretrained(args.model_name_or_path, cache_dir=args.cache_dir)
else:
config = config_class()
config.num_hidden_layers = args.num_hidden_layers
config.hidden_size = args.hidden_size
args.train_data_file = "./cache/train.raw"
args.eval_data_file = "./cache/test.raw"
# Here is the place where we start to change the tokenizer
if args.tokenizer_name:
tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name, cache_dir=args.cache_dir)
elif args.model_name_or_path:
tokenizer = tokenizer_class.from_pretrained(args.model_name_or_path, cache_dir=args.cache_dir)
else:
raise ValueError(
"You are instantiating a new {} tokenizer. This is not supported, but you can do it from another script, "
"save it,"
"and load it from here, using --tokenizer_name".format(tokenizer_class.__name__)
)
if args.vocab_file:
tokenizer.build_vocab_file(args.vocab_file, args.event_type)
if args.block_size <= 0:
args.block_size = tokenizer.max_len
# Our input block size will be the max possible for the model
else:
args.block_size = min(args.block_size, tokenizer.max_len)
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,
)
else:
logger.info("Training new model from scratch")
model = model_class(config=config)
model.to(args.device)
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 = load_and_cache_examples(args, tokenizer, evaluate=False)
if args.local_rank == 0:
torch.distributed.barrier()
global_step, tr_loss = train(args, train_dataset, model, tokenizer)
logger.info(" global_step = %s, average loss = %s", global_step, tr_loss)
# Saving best-practices: if you use save_pretrained for the model and tokenizer, you can reload them using
# from_pretrained()
if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0):
# Create output directory if needed
if args.local_rank in [-1, 0]:
os.makedirs(args.output_dir, exist_ok=True)
logger.info("Saving model checkpoint to %s", args.output_dir)
# Save a trained model, configuration and tokenizer using `save_pretrained()`.
# They can then be reloaded using `from_pretrained()`
model_to_save = (
model.module if hasattr(model, "module") else model
) # Take care of distributed/parallel training
model_to_save.save_pretrained(args.output_dir)
tokenizer.save_pretrained(args.output_dir)
# Good practice: save your training arguments together with the trained model
torch.save(args, os.path.join(args.output_dir, "training_args.bin"))
# Load a trained model and vocabulary that you have fine-tuned
model = model_class.from_pretrained(args.output_dir)
tokenizer = tokenizer_class.from_pretrained(args.output_dir)
model.to(args.device)
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
checkpoints = [args.output_dir]
if args.eval_all_checkpoints:
checkpoints = list(
os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME, recursive=True))
)
logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN) # Reduce logging
logger.info("Evaluate the following checkpoints: %s", checkpoints)
for checkpoint in checkpoints:
global_step = checkpoint.split("-")[-1] if len(checkpoints) > 1 else ""
prefix = checkpoint.split("/")[-1] if checkpoint.find("checkpoint") != -1 else ""
model = model_class.from_pretrained(checkpoint)
model.to(args.device)
result = evaluate(args, model, tokenizer, prefix=prefix)
result = dict((k + "_{}".format(global_step), v) for k, v in result.items())
results.update(result)
return results