in movement-pruning/masked_run_glue.py [0:0]
def main():
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help="The input data dir. Should contain the .tsv files (or other data files) for the task.",
)
parser.add_argument(
"--model_type",
default=None,
type=str,
required=True,
help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()),
)
parser.add_argument(
"--model_name_or_path",
default=None,
type=str,
required=True,
help="Path to pretrained model or model identifier from huggingface.co/models",
)
parser.add_argument(
"--task_name",
default=None,
type=str,
required=True,
help="The name of the task to train selected in the list: " + ", ".join(processors.keys()),
)
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(
"--config_name",
default="",
type=str,
help="Pretrained config name or path if not the same as model_name",
)
parser.add_argument(
"--tokenizer_name",
default="",
type=str,
help="Pretrained tokenizer name or path if not the same as model_name",
)
parser.add_argument(
"--cache_dir",
default="",
type=str,
help="Where do you want to store the pre-trained models downloaded from huggingface.co",
)
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help=(
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded."
),
)
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(
"--do_lower_case",
action="store_true",
help="Set this flag if you are using an uncased model.",
)
parser.add_argument(
"--per_gpu_train_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for training.",
)
parser.add_argument(
"--per_gpu_eval_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for evaluation.",
)
parser.add_argument("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.")
# Pruning parameters
parser.add_argument(
"--mask_scores_learning_rate",
default=1e-2,
type=float,
help="The Adam initial learning rate of the mask scores.",
)
parser.add_argument(
"--initial_threshold", default=1.0, type=float, help="Initial value of the threshold (for scheduling)."
)
parser.add_argument(
"--final_threshold", default=0.7, type=float, help="Final value of the threshold (for scheduling)."
)
parser.add_argument(
"--initial_warmup",
default=1,
type=int,
help=(
"Run `initial_warmup` * `warmup_steps` steps of threshold warmup during which threshold stays "
"at its `initial_threshold` value (sparsity schedule)."
),
)
parser.add_argument(
"--final_warmup",
default=2,
type=int,
help=(
"Run `final_warmup` * `warmup_steps` steps of threshold cool-down during which threshold stays "
"at its final_threshold value (sparsity schedule)."
),
)
parser.add_argument(
"--pruning_method",
default="topK",
type=str,
help=(
"Pruning Method (l0 = L0 regularization, magnitude = Magnitude pruning, topK = Movement pruning,"
" sigmoied_threshold = Soft movement pruning)."
),
)
parser.add_argument(
"--mask_init",
default="constant",
type=str,
help="Initialization method for the mask scores. Choices: constant, uniform, kaiming.",
)
parser.add_argument(
"--mask_scale", default=0.0, type=float, help="Initialization parameter for the chosen initialization method."
)
parser.add_argument("--regularization", default=None, help="Add L0 or L1 regularization to the mask scores.")
parser.add_argument(
"--final_lambda",
default=0.0,
type=float,
help="Regularization intensity (used in conjunction with `regularization`.",
)
parser.add_argument("--global_topk", action="store_true", help="Global TopK on the Scores.")
parser.add_argument(
"--global_topk_frequency_compute",
default=25,
type=int,
help="Frequency at which we compute the TopK global threshold.",
)
# Distillation parameters (optional)
parser.add_argument(
"--teacher_type",
default=None,
type=str,
help=(
"Teacher type. Teacher tokenizer and student (model) tokenizer must output the same tokenization. Only for"
" distillation."
),
)
parser.add_argument(
"--teacher_name_or_path",
default=None,
type=str,
help="Path to the already fine-tuned teacher model. Only for distillation.",
)
parser.add_argument(
"--alpha_ce", default=0.5, type=float, help="Cross entropy loss linear weight. Only for distillation."
)
parser.add_argument(
"--alpha_distil", default=0.5, type=float, help="Distillation loss linear weight. Only for distillation."
)
parser.add_argument(
"--temperature", default=2.0, type=float, help="Distillation temperature. Only for distillation."
)
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("--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=3.0,
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(
"--eval_all_checkpoints",
action="store_true",
help="Evaluate all checkpoints starting with the same prefix as model_name 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()
# Regularization
if args.regularization == "null":
args.regularization = None
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(
f"Output directory ({args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to"
" overcome."
)
# 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 synchronizing 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)
# Prepare GLUE task
args.task_name = args.task_name.lower()
if args.task_name not in processors:
raise ValueError("Task not found: %s" % (args.task_name))
processor = processors[args.task_name]()
args.output_mode = output_modes[args.task_name]
label_list = processor.get_labels()
num_labels = len(label_list)
# Load pretrained model and tokenizer
if args.local_rank not in [-1, 0]:
torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab
args.model_type = args.model_type.lower()
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,
num_labels=num_labels,
finetuning_task=args.task_name,
cache_dir=args.cache_dir if args.cache_dir else None,
pruning_method=args.pruning_method,
mask_init=args.mask_init,
mask_scale=args.mask_scale,
)
tokenizer = tokenizer_class.from_pretrained(
args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
cache_dir=args.cache_dir if args.cache_dir else None,
do_lower_case=args.do_lower_case,
)
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,
)
if args.teacher_type is not None:
assert args.teacher_name_or_path is not None
assert args.alpha_distil > 0.0
assert args.alpha_distil + args.alpha_ce > 0.0
teacher_config_class, teacher_model_class, _ = MODEL_CLASSES[args.teacher_type]
teacher_config = teacher_config_class.from_pretrained(args.teacher_name_or_path)
teacher = teacher_model_class.from_pretrained(
args.teacher_name_or_path,
from_tf=False,
config=teacher_config,
cache_dir=args.cache_dir if args.cache_dir else None,
)
teacher.to(args.device)
else:
teacher = None
if args.local_rank == 0:
torch.distributed.barrier() # Make sure only the first process in distributed training will download model & vocab
model.to(args.device)
logger.info("Training/evaluation parameters %s", args)
# Training
if args.do_train:
train_dataset = load_and_cache_examples(args, args.task_name, tokenizer, evaluate=False)
global_step, tr_loss = train(args, train_dataset, model, tokenizer, teacher=teacher)
logger.info(" global_step = %s, average loss = %s", global_step, tr_loss)
# Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained()
if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0):
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, do_lower_case=args.do_lower_case)
model.to(args.device)
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
tokenizer = tokenizer_class.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
checkpoints = [args.output_dir]
if args.eval_all_checkpoints:
checkpoints = [
os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME, recursive=True))
]
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 = {k + "_{}".format(global_step): v for k, v in result.items()}
results.update(result)
return results