Beginning of GLUE script
This commit is contained in:
LysandreJik
@@ -0,0 +1,253 @@
|
||||
# coding=utf-8
|
||||
# Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team.
|
||||
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
""" Finetuning the library models for sequence classification on GLUE (Bert, XLM, XLNet, RoBERTa)."""
|
||||
|
||||
from __future__ import absolute_import, division, print_function
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import os
|
||||
import random
|
||||
|
||||
import numpy as np
|
||||
import tensorflow as tf
|
||||
|
||||
from pytorch_transformers import (BertConfig, TFBertForSequenceClassification, BertTokenizer)
|
||||
from utils_glue import (compute_metrics, convert_examples_to_features,
|
||||
output_modes, processors)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig,)), ())
|
||||
MODEL_CLASSES = {
|
||||
'bert': (BertConfig, TFBertForSequenceClassification, BertTokenizer),
|
||||
}
|
||||
|
||||
|
||||
def set_seed(args):
|
||||
random.seed(args.seed)
|
||||
np.random.seed(args.seed)
|
||||
tf.random.set_seed(args.seed)
|
||||
|
||||
|
||||
def load_and_cache_examples(args, task, tokenizer, evaluate=False):
|
||||
processor = processors[task]()
|
||||
output_mode = output_modes[task]
|
||||
|
||||
# Load data features from cache or dataset file
|
||||
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']:
|
||||
# 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, label_list, args.max_seq_length, tokenizer, output_mode,
|
||||
cls_token_at_end=bool(args.model_type in ['xlnet']), # xlnet has a cls token at the end
|
||||
cls_token=tokenizer.cls_token,
|
||||
cls_token_segment_id=2 if args.model_type in ['xlnet'] else 0,
|
||||
sep_token=tokenizer.sep_token,
|
||||
sep_token_extra=bool(args.model_type in ['roberta']), # roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
|
||||
pad_on_left=bool(args.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 args.model_type in ['xlnet'] else 0,
|
||||
)
|
||||
|
||||
# Convert to Tensors and build dataset
|
||||
all_input_ids = tf.constant([f.input_ids for f in features])
|
||||
all_input_mask = tf.constant([f.input_mask for f in features])
|
||||
all_segment_ids = tf.constant([f.segment_ids for f in features])
|
||||
if output_mode == "classification":
|
||||
all_label_ids = tf.constant([f.label_id for f in features])
|
||||
elif output_mode == "regression":
|
||||
all_label_ids = tf.constant([f.label_id for f in features])
|
||||
|
||||
if not evaluate:
|
||||
dataset = tf.data.Dataset.from_tensor_slices(({
|
||||
"input_ids": all_input_ids,
|
||||
"input_mask": all_input_mask,
|
||||
"segment_ids": all_segment_ids
|
||||
}, all_label_ids))
|
||||
return dataset
|
||||
else:
|
||||
dataset = tf.data.Dataset.from_tensor_slices({
|
||||
"input_ids": all_input_ids,
|
||||
"input_mask": all_input_mask,
|
||||
"segment_ids": all_segment_ids
|
||||
})
|
||||
return dataset, all_label_ids
|
||||
|
||||
|
||||
def train(args, train_dataset, model):
|
||||
""" Train the model """
|
||||
return model.fit(train_dataset.batch(args.per_gpu_train_batch_size))
|
||||
|
||||
|
||||
def evaluate(args, model, tokenizer, prefix=""):
|
||||
# Loop to handle MNLI double evaluation (matched, mis-matched)
|
||||
eval_task_names = ("mnli", "mnli-mm") if args.task_name == "mnli" else (args.task_name,)
|
||||
eval_outputs_dirs = (args.output_dir, args.output_dir + '-MM') if args.task_name == "mnli" else (args.output_dir,)
|
||||
|
||||
results = {}
|
||||
for eval_task, eval_output_dir in zip(eval_task_names, eval_outputs_dirs):
|
||||
evaluation_x, evaluation_y = load_and_cache_examples(args, eval_task, tokenizer, evaluate=True)
|
||||
|
||||
if not os.path.exists(eval_output_dir) and args.local_rank in [-1, 0]:
|
||||
os.makedirs(eval_output_dir)
|
||||
|
||||
# Eval!
|
||||
logger.info("***** Running evaluation {} *****".format(prefix))
|
||||
logger.info(" Num examples = %d", len(list(evaluation_x)))
|
||||
logger.info(" Batch size = %d", args.per_gpu_eval_batch_size)
|
||||
|
||||
# predictions = model.predict(evaluation_x.batch(args.per_gpu_eval_batch_size))
|
||||
predictions = model(list(evaluation_x.batch(3))[0])
|
||||
np_predictions = np.argmax(predictions, axis=1)
|
||||
result = compute_metrics(args.task_name, np_predictions, evaluation_y.numpy())
|
||||
results.update(result)
|
||||
|
||||
logger.info("***** Eval results {} *****".format(prefix))
|
||||
for key in sorted(result.keys()):
|
||||
logger.info(" %s = %s", key, str(result[key]))
|
||||
|
||||
return results
|
||||
|
||||
|
||||
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 pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_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 s3")
|
||||
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="Rul 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('--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=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")
|
||||
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()
|
||||
|
||||
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 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)
|
||||
|
||||
# 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)
|
||||
|
||||
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)
|
||||
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)
|
||||
model = model_class.from_pretrained(args.model_name_or_path, config=config)
|
||||
|
||||
logger.info("Training/evaluation parameters %s", args)
|
||||
|
||||
model.compile(loss='categorical_crossentropy', optimize='adam')
|
||||
|
||||
# Training
|
||||
if args.do_train:
|
||||
train_dataset = load_and_cache_examples(args, args.task_name, tokenizer, evaluate=False)
|
||||
train(args, train_dataset, model)
|
||||
|
||||
# Evaluation
|
||||
results = {}
|
||||
if args.do_eval:
|
||||
result = evaluate(args, model, tokenizer)
|
||||
print(result)
|
||||
|
||||
return results
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user