def load_and_cache_examples(args, task, tokenizer, evaluate=False):
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache
processor = processors[task]()
output_mode = output_modes[task]
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir,
"cached_{}_{}_{}_{}".format(
"dev" if evaluate else "train",
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length),
str(task),
),
)
label_list = processor.get_labels()
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s", cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
if task in ["mnli", "mnli-mm"] and args.model_type in ["roberta"]:
# HACK(label indices are swapped in RoBERTa pretrained model)
label_list[1], label_list[2] = label_list[2], label_list[1]
examples = (
processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
)
features = convert_examples_to_features(
examples,
tokenizer,
label_list=label_list,
max_length=args.max_seq_length,
output_mode=output_mode,
pad_on_left=bool(args.model_type in ["xlnet"]), # pad on the left for xlnet
pad_token=tokenizer.pad_token_id,
pad_token_segment_id=tokenizer._convert_token_to_id('[PAD]'),
#pad_token_segment_id=tokenizer.pad_token_type_id,
)
if args.local_rank in [-1, 0]:
logger.info("Saving features into cached file %s", cached_features_file)
torch.save(features, cached_features_file)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long)
all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long)
if output_mode == "classification":
all_labels = torch.tensor([f.label for f in features], dtype=torch.long)
elif output_mode == "regression":
all_labels = torch.tensor([f.label for f in features], dtype=torch.float)
all_pair_ids = torch.tensor([int(f.pairID) for f in features], dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_labels, all_pair_ids)
return dataset, label_list
def load_and_cache_examples(data_dir, max_seq_length, model_type, model_name_or_path, tokenizer, overwrite_cache):
processor = HansProcessor()
# Load data features from cache or dataset file
cached_features_file = os.path.join(
data_dir,
"cached_{}_{}_{}_{}".format(
"dev" if evaluate else "train",
list(filter(None, model_name_or_path.split("/"))).pop(),
str(max_seq_length),
"hans",
),
)
label_list = processor.get_labels()
if os.path.exists(cached_features_file) and not overwrite_cache:
logger.info("Loading features from cached file %s", cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", data_dir)
if model_type in ["roberta"]:
# HACK(label indices are swapped in RoBERTa pretrained model)
label_list[1], label_list[2] = label_list[2], label_list[1]
examples = (
processor.get_dev_examples(data_dir)
)
features = convert_examples_to_features(
examples,
tokenizer,
label_list=label_list,
max_length=max_seq_length,
output_mode="classification",
pad_on_left=bool(model_type in ["xlnet"]), # pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
pad_token_segment_id=4 if model_type in ["xlnet"] else 0,
)
logger.info("Saving features into cached file %s", cached_features_file)
torch.save(features, cached_features_file)
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_attention_mask = torch.tensor([f.attention_mask for f in features], dtype=torch.long)
all_token_type_ids = torch.tensor([f.token_type_ids for f in features], dtype=torch.long)
all_labels = torch.tensor([f.label for f in features], dtype=torch.long)
all_pair_ids = torch.tensor([int(f.pairID) for f in features], dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_attention_mask, all_token_type_ids, all_labels, all_pair_ids)
return dataset, label_list
