SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge branch 'master' into generation_sampler

Browse Source
This commit is contained in:
thomwolf
2019-12-21 14:12:52 +01:00
parent 300ec3003c 8618bf15d6
commit cfa0380515
137 changed files with 8389 additions and 1368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
examples/README.md
View File

@@ -24,8 +24,6 @@ pip install -r ./examples/requirements.txt
| [Multiple Choice](#multiple-choice) | Examples running BERT/XLNet/RoBERTa on the SWAG/RACE/ARC tasks.
| [Named Entity Recognition](#named-entity-recognition) | Using BERT for Named Entity Recognition (NER) on the CoNLL 2003 dataset, examples with distributed training. |
| [XNLI](#xnli) | Examples running BERT/XLM on the XNLI benchmark. |
| [Abstractive summarization](#abstractive-summarization) | Using the BertAbs
model finetuned on the CNN/DailyMail dataset to generate summaries. |
## TensorFlow 2.0 Bert models on GLUE
@@ -469,7 +467,7 @@ Training with the previously defined hyper-parameters yields the following resul
## Named Entity Recognition
Based on the scripts [`run_ner.py`](https://github.com/huggingface/transformers/blob/master/examples/run_ner.py) for Pytorch and
[`run_tf_ner.py`(https://github.com/huggingface/transformers/blob/master/examples/run_tf_ner.py)] for Tensorflow 2.
[`run_tf_ner.py`](https://github.com/huggingface/transformers/blob/master/examples/run_tf_ner.py) for Tensorflow 2.
This example fine-tune Bert Multilingual on GermEval 2014 (German NER).
Details and results for the fine-tuning provided by @stefan-it.
@@ -646,34 +644,6 @@ micro avg 0.8722 0.8774 0.8748 13869
macro avg 0.8712 0.8774 0.8740 13869
```
## Abstractive summarization
Based on the script
[`run_summarization_finetuning.py`](https://github.com/huggingface/transformers/blob/master/examples/run_summarization_finetuning.py).
Before running this script you should download **both** CNN and Daily Mail
datasets from [Kyunghyun Cho's website](https://cs.nyu.edu/~kcho/DMQA/) (the
links next to "Stories") in the same folder. Then uncompress the archives by running:
```bash
tar -xvf cnn_stories.tgz && tar -xvf dailymail_stories.tgz
```
note that the finetuning script **will not work** if you do not download both
datasets. We will refer as `$DATA_PATH` the path to where you uncompressed both
archive.
```bash
export DATA_PATH=/path/to/dataset/
python run_summarization_finetuning.py \
--output_dir=output \
--model_type=bert2bert \
--model_name_or_path=bert2bert \
--do_train \
--data_path=$DATA_PATH \
```
## XNLI
Based on the script [`run_xnli.py`](https://github.com/huggingface/transformers/blob/master/examples/run_xnli.py).

7
examples/run_generation.py
View File

@@ -212,9 +212,10 @@ def main():
repetition_penalty=args.repetition_penalty,
)
generated_sequence = output_sequences.tolist()
text = [tokenizer.decode(seq, clean_up_tokenization_spaces=True) for seq in generated_sequence]
# text = text[: text.find(args.stop_token) if args.stop_token else None]
# Batch size == 1. to add more examples please use num_return_sequences > 1
generated_sequence = output_sequences[0].tolist()
text = tokenizer.decode(generated_sequence, clean_up_tokenization_spaces=True)
text = text[: t.find(args.stop_token) if args.stop_token else None]
print(text)

12
examples/run_glue.py
View File

@@ -52,6 +52,9 @@ from transformers import (WEIGHTS_NAME, BertConfig,
AlbertConfig,
AlbertForSequenceClassification,
AlbertTokenizer,
XLMRobertaConfig,
XLMRobertaForSequenceClassification,
XLMRobertaTokenizer,
)
from transformers import AdamW, get_linear_schedule_with_warmup
@@ -72,7 +75,8 @@ MODEL_CLASSES = {
'xlm': (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
'roberta': (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer),
'distilbert': (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer),
'albert': (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer)
'albert': (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer),
'xlmroberta': (XLMRobertaConfig, XLMRobertaForSequenceClassification, XLMRobertaTokenizer),
}
@@ -304,9 +308,9 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
label_list = processor.get_labels()
if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta']:
if task in ['mnli', 'mnli-mm'] and args.model_type in ['roberta', 'xlmroberta']:
# HACK(label indices are swapped in RoBERTa pretrained model)
label_list[1], label_list[2] = label_list[2], label_list[1]
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,
@@ -380,7 +384,7 @@ def main():
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.")
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,

2
examples/run_lm_finetuning.py
View File

@@ -430,7 +430,7 @@ def main():
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.")
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,

5
examples/run_ner.py
View File

@@ -38,11 +38,13 @@ from transformers import WEIGHTS_NAME, BertConfig, BertForTokenClassification, B
from transformers import RobertaConfig, RobertaForTokenClassification, RobertaTokenizer
from transformers import DistilBertConfig, DistilBertForTokenClassification, DistilBertTokenizer
from transformers import CamembertConfig, CamembertForTokenClassification, CamembertTokenizer
from transformers import XLMRobertaConfig, XLMRobertaForTokenClassification, XLMRobertaTokenizer
logger = logging.getLogger(__name__)
ALL_MODELS = sum(
(tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, RobertaConfig, DistilBertConfig)),
(tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, RobertaConfig, DistilBertConfig,
CamembertConfig, XLMRobertaConfig)),
())
MODEL_CLASSES = {
@@ -50,6 +52,7 @@ MODEL_CLASSES = {
"roberta": (RobertaConfig, RobertaForTokenClassification, RobertaTokenizer),
"distilbert": (DistilBertConfig, DistilBertForTokenClassification, DistilBertTokenizer),
"camembert": (CamembertConfig, CamembertForTokenClassification, CamembertTokenizer),
"xlmroberta": (XLMRobertaConfig, XLMRobertaForTokenClassification, XLMRobertaTokenizer),
}

44
examples/run_squad.py
View File

@@ -61,7 +61,6 @@ MODEL_CLASSES = {
'xlm': (XLMConfig, XLMForQuestionAnswering, XLMTokenizer),
'distilbert': (DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer),
'albert': (AlbertConfig, AlbertForQuestionAnswering, AlbertTokenizer),
'xlm': (XLMConfig, XLMForQuestionAnswering, XLMTokenizer)
}
def set_seed(args):
@@ -223,7 +222,7 @@ def evaluate(args, model, tokenizer, prefix=""):
eval_dataloader = DataLoader(dataset, sampler=eval_sampler, batch_size=args.eval_batch_size)
# multi-gpu evaluate
if args.n_gpu > 1:
if args.n_gpu > 1 and not isinstance(model, torch.nn.DataParallel):
model = torch.nn.DataParallel(model)
# Eval!
@@ -299,10 +298,13 @@ def evaluate(args, model, tokenizer, prefix=""):
# XLNet and XLM use a more complex post-processing procedure
if args.model_type in ['xlnet', 'xlm']:
start_n_top = model.config.start_n_top if hasattr(model, "config") else model.module.config.start_n_top
end_n_top = model.config.end_n_top if hasattr(model, "config") else model.module.config.end_n_top
predictions = compute_predictions_log_probs(examples, features, all_results, args.n_best_size,
args.max_answer_length, output_prediction_file,
output_nbest_file, output_null_log_odds_file,
model.config.start_n_top, model.config.end_n_top,
start_n_top, end_n_top,
args.version_2_with_negative, tokenizer, args.verbose_logging)
else:
predictions = compute_predictions_logits(examples, features, all_results, args.n_best_size,
@@ -334,7 +336,7 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
else:
logger.info("Creating features from dataset file at %s", input_dir)
if not args.data_dir:
if not args.data_dir and ((evaluate and not args.predict_file) or (not evaluate and not args.train_file)):
try:
import tensorflow_datasets as tfds
except ImportError:
@@ -347,7 +349,11 @@ def load_and_cache_examples(args, tokenizer, evaluate=False, output_examples=Fal
examples = SquadV1Processor().get_examples_from_dataset(tfds_examples, evaluate=evaluate)
else:
processor = SquadV2Processor() if args.version_2_with_negative else SquadV1Processor()
examples = processor.get_dev_examples(args.data_dir) if evaluate else processor.get_train_examples(args.data_dir)
if evaluate:
examples = processor.get_dev_examples(args.data_dir, filename=args.predict_file)
else:
examples = processor.get_train_examples(args.data_dir, filename=args.train_file)
features, dataset = squad_convert_examples_to_features(
examples=examples,
@@ -384,7 +390,14 @@ def main():
## Other parameters
parser.add_argument("--data_dir", default=None, type=str,
help="The input data dir. Should contain the .json files for the task. If not specified, will run with tensorflow_datasets.")
help="The input data dir. Should contain the .json files for the task." +
"If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
parser.add_argument("--train_file", default=None, type=str,
help="The input training file. If a data dir is specified, will look for the file there" +
"If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
parser.add_argument("--predict_file", default=None, type=str,
help="The input evaluation file. If a data dir is specified, will look for the file there" +
"If no data dir or train/predict files are specified, will run with tensorflow_datasets.")
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,
@@ -469,11 +482,6 @@ def main():
parser.add_argument('--server_port', type=str, default='', help="Can be used for distant debugging.")
args = parser.parse_args()
args.predict_file = os.path.join(args.output_dir, 'predictions_{}_{}.txt'.format(
list(filter(None, args.model_name_or_path.split('/'))).pop(),
str(args.max_seq_length))
)
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))
@@ -571,10 +579,16 @@ def main():
# Evaluation - we can ask to evaluate all the checkpoints (sub-directories) in a directory
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 model loading logs
if args.do_train:
logger.info("Loading checkpoints saved during training for evaluation")
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 model loading logs
else:
logger.info("Loading checkpoint %s for evaluation", args.model_name_or_path)
checkpoints = [args.model_name_or_path]
logger.info("Evaluate the following checkpoints: %s", checkpoints)

6
examples/summarization/README.md
View File

@@ -29,7 +29,7 @@ And move all the stories to the same folder. We will refer as `$DATA_PATH` the p
python run_summarization.py \
--documents_dir $DATA_PATH \
--summaries_output_dir $SUMMARIES_PATH \ # optional
--to_cpu false \
--no_cuda false \
--batch_size 4 \
--min_length 50 \
--max_length 200 \
@@ -39,7 +39,7 @@ python run_summarization.py \
--compute_rouge true
```
The scripts executes on GPU if one is available and if `to_cpu` is not set to `true`. Inference on multiple GPUs is not suported yet. The ROUGE scores will be displayed in the console at the end of evaluation and written in a `rouge_scores.txt` file. The script takes 30 hours to compute with a single Tesla V100 GPU and a batch size of 10 (300,000 texts to summarize).
The scripts executes on GPU if one is available and if `no_cuda` is not set to `true`. Inference on multiple GPUs is not suported yet. The ROUGE scores will be displayed in the console at the end of evaluation and written in a `rouge_scores.txt` file. The script takes 30 hours to compute with a single Tesla V100 GPU and a batch size of 10 (300,000 texts to summarize).
## Summarize any text
@@ -49,7 +49,7 @@ Put the documents that you would like to summarize in a folder (the path to whic
python run_summarization.py \
--documents_dir $DATA_PATH \
--summaries_output_dir $SUMMARIES_PATH \ # optional
--to_cpu false \
--no_cuda false \
--batch_size 4 \
--min_length 50 \
--max_length 200 \

50
examples/summarization/configuration_bertabs.py
View File

@@ -33,6 +33,8 @@ class BertAbsConfig(PretrainedConfig):
r""" Class to store the configuration of the BertAbs model.
Arguments:
vocab_size: int
Number of tokens in the vocabulary.
max_pos: int
The maximum sequence length that this model will be used with.
enc_layer: int
@@ -65,7 +67,7 @@ class BertAbsConfig(PretrainedConfig):
def __init__(
self,
vocab_size_or_config_json_file=30522,
vocab_size=30522,
max_pos=512,
enc_layers=6,
enc_hidden_size=512,
@@ -81,39 +83,17 @@ class BertAbsConfig(PretrainedConfig):
):
super(BertAbsConfig, self).__init__(**kwargs)
if self._input_is_path_to_json(vocab_size_or_config_json_file):
path_to_json = vocab_size_or_config_json_file
with open(path_to_json, "r", encoding="utf-8") as reader:
json_config = json.loads(reader.read())
for key, value in json_config.items():
self.__dict__[key] = value
elif isinstance(vocab_size_or_config_json_file, int):
self.vocab_size = vocab_size_or_config_json_file
self.max_pos = max_pos
self.vocab_size = vocab_size
self.max_pos = max_pos
self.enc_layers = enc_layers
self.enc_hidden_size = enc_hidden_size
self.enc_heads = enc_heads
self.enc_ff_size = enc_ff_size
self.enc_dropout = enc_dropout
self.enc_layers = enc_layers
self.enc_hidden_size = enc_hidden_size
self.enc_heads = enc_heads
self.enc_ff_size = enc_ff_size
self.enc_dropout = enc_dropout
self.dec_layers = dec_layers
self.dec_hidden_size = dec_hidden_size
self.dec_heads = dec_heads
self.dec_ff_size = dec_ff_size
self.dec_dropout = dec_dropout
else:
raise ValueError(
"First argument must be either a vocabulary size (int)"
"or the path to a pretrained model config file (str)"
)
def _input_is_path_to_json(self, first_argument):
""" Checks whether the first argument passed to config
is the path to a JSON file that contains the config.
"""
is_python_2 = sys.version_info[0] == 2
if is_python_2:
return isinstance(first_argument, unicode)
else:
return isinstance(first_argument, str)
self.dec_layers = dec_layers
self.dec_hidden_size = dec_hidden_size
self.dec_heads = dec_heads
self.dec_ff_size = dec_ff_size
self.dec_dropout = dec_dropout