franziska/MasterarbeitCode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

initial commit of project

Browse Source
This commit is contained in:
Franziska Marquis
2021-04-11 19:51:12 +02:00
commit a21a8186d9
110 changed files with 16326178 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

333
train_model/language_modeling.py Normal file
View File

@@ -0,0 +1,333 @@
# 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.
"""
Fine-tuning the library models for language modeling on a text file (GPT, GPT-2, BERT, RoBERTa).
GPT and GPT-2 are fine-tuned using a causal language modeling (CLM) loss while BERT and RoBERTa are fine-tuned
using a masked language modeling (MLM) loss.
"""
# https://github.com/huggingface/transformers/blob/v2.9.1/examples/language-modeling/run_language_modeling.py
import time
from pathlib import Path
'''
Modified huggingface code for pretraining FoodBERT.
Running parameters:
--output_dir=output --model_type=bert --model_name=bert-base-german-cased --do_train
--train_data_file="data/training_data.txt" --do_eval --eval_data_file="data/testing_data.txt"
--mlm --line_by_line --per_device_train_batch_size=8 --gradient_accumulation_steps=2 --per_device_eval_batch_size=8
--save_total_limit=5 --save_steps=10000 --logging_steps=10000 --evaluation_strategy=epoch
--model_name_or_path="bert-base-german-cased"
may need adjustment (especially paths)
'''
import json
import logging
import math
import os
import pickle
from dataclasses import dataclass, field
from typing import Optional
from transformers import BertTokenizer
from transformers import (
CONFIG_MAPPING,
MODEL_WITH_LM_HEAD_MAPPING,
AutoConfig,
AutoModelForMaskedLM,
AutoTokenizer,
DataCollatorForLanguageModeling,
HfArgumentParser,
LineByLineTextDataset,
PreTrainedTokenizer,
TextDataset,
Trainer,
TrainingArguments,
set_seed, BertTokenizer,
)
logger = logging.getLogger(__name__)
MODEL_CONFIG_CLASSES = list(MODEL_WITH_LM_HEAD_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
class CachedLineByLineTextDataset(LineByLineTextDataset):
"""
Adds caching functionality to LineByLineTextDataset
"""
def __init__(self, tokenizer: PreTrainedTokenizer, file_path: str, block_size: int, local_rank=-1):
assert os.path.isfile(file_path)
cached_file_path = Path(file_path.rsplit('.', 1)[0] + '_cache.pth')
if cached_file_path.exists():
with cached_file_path.open('rb') as f:
self.examples = pickle.load(f)
logger.info(
f"Loading features from cached file {cached_file_path}")
else:
logger.info("Creating features from dataset file at %s", file_path)
with open(file_path, encoding="utf-8") as f:
lines = [line for line in f.read().splitlines() if (len(line) > 0 and not line.isspace())]
batch_encoding = tokenizer.batch_encode_plus(lines, add_special_tokens=True, max_length=block_size, truncation=True)
self.examples = batch_encoding["input_ids"]
with cached_file_path.open('wb') as f:
pickle.dump(self.examples, f, protocol=pickle.HIGHEST_PROTOCOL)
logger.info(
f"Saving features into cached file {cached_file_path}")
@dataclass
class ModelArguments:
"""
Arguments pertaining to which model/config/tokenizer we are going to fine-tune, or train from scratch.
"""
model_name_or_path: Optional[str] = field(
default=None,
metadata={
"help": "The model checkpoint for weights initialization. Leave None if you want to train a model from scratch."
},
)
model_type: Optional[str] = field(
default=None,
metadata={"help": "If training from scratch, pass a model type from the list: " + ", ".join(MODEL_TYPES)},
)
config_name: Optional[str] = field(
default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
)
tokenizer_name: Optional[str] = field(
default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
)
cache_dir: Optional[str] = field(
default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
)
@dataclass
class DataTrainingArguments:
"""
Arguments pertaining to what data we are going to input our model for training and eval.
"""
train_data_file: Optional[str] = field(
default=None, metadata={"help": "The input training data file (a text file)."}
)
eval_data_file: Optional[str] = field(
default=None,
metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
)
line_by_line: bool = field(
default=False,
metadata={"help": "Whether distinct lines of text in the dataset are to be handled as distinct sequences."},
)
mlm: bool = field(
default=False, metadata={"help": "Train with masked-language modeling loss instead of language modeling."}
)
mlm_probability: float = field(
default=0.15, metadata={"help": "Ratio of tokens to mask for masked language modeling loss"}
)
block_size: int = field(
default=-1,
metadata={
"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)."
},
)
overwrite_cache: bool = field(
default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
)
def get_dataset(args: DataTrainingArguments, tokenizer: PreTrainedTokenizer, evaluate=False, local_rank=-1):
file_path = args.eval_data_file if evaluate else args.train_data_file
if args.line_by_line:
return CachedLineByLineTextDataset(
tokenizer=tokenizer, file_path=file_path, block_size=args.block_size, local_rank=local_rank
)
else:
return TextDataset(
tokenizer=tokenizer, file_path=file_path, block_size=args.block_size, local_rank=local_rank,
)
def main():
print("start time: " + time.strftime('%d.%m %H:%M'))
# See all possible arguments in src/transformers/training_args.py
# or by passing the --help flag to this script.
# We now keep distinct sets of args, for a cleaner separation of concerns.
parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
if data_args.eval_data_file is None and training_args.do_eval:
raise ValueError(
"Cannot do evaluation without an evaluation data file. Either supply a file to --eval_data_file "
"or remove the --do_eval argument."
)
if (
os.path.exists(training_args.output_dir)
and os.listdir(training_args.output_dir)
and training_args.do_train
and not training_args.overwrite_output_dir
):
raise ValueError(
f"Output directory ({training_args.output_dir}) already exists and is not empty. Use --overwrite_output_dir to overcome."
)
# Setup logging
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO if training_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",
training_args.local_rank,
training_args.device,
training_args.n_gpu,
bool(training_args.local_rank != -1),
training_args.fp16,
)
logger.info("Training/evaluation parameters %s", training_args)
# Set seed
set_seed(training_args.seed)
# Load pretrained model and tokenizer
#
# Distributed training:
# The .from_pretrained methods guarantee that only one local process can concurrently
# download model & vocab.
if model_args.config_name:
config = AutoConfig.from_pretrained(model_args.config_name, cache_dir=model_args.cache_dir)
elif model_args.model_name_or_path:
config = AutoConfig.from_pretrained(model_args.model_name_or_path, cache_dir=model_args.cache_dir)
else:
config = CONFIG_MAPPING[model_args.model_type]()
logger.warning("You are instantiating a new config instance from scratch.")
with open("train_model/vocab/used_ingredients.json", "r") as used_ingredients_file:
used_ingredients = json.load(used_ingredients_file)
tokenizer = BertTokenizer(vocab_file='train_model/vocab/vocab.txt', do_lower_case=False, model_max_length=512, never_split=used_ingredients)
if model_args.model_name_or_path:
model = AutoModelForMaskedLM.from_pretrained(
model_args.model_name_or_path,
from_tf=bool(".ckpt" in model_args.model_name_or_path),
config=config,
cache_dir=model_args.cache_dir,
)
else:
logger.info("Training new model from scratch")
model = AutoModelForMaskedLM.from_config(config)
model.resize_token_embeddings(len(tokenizer))
if config.model_type in ["bert", "roberta", "distilbert", "camembert"] and not data_args.mlm:
raise ValueError(
"BERT and RoBERTa-like models do not have LM heads but masked LM heads. They must be run using the --mlm "
"flag (masked language modeling)."
)
if data_args.block_size <= 0:
data_args.block_size = tokenizer.model_max_length
# Our input block size will be the max possible for the model
else:
data_args.block_size = min(data_args.block_size, tokenizer.model_max_length)
# Get datasets
train_dataset = (
get_dataset(data_args, tokenizer=tokenizer, local_rank=training_args.local_rank)
if training_args.do_train
else None
)
eval_dataset = (
get_dataset(data_args, tokenizer=tokenizer, local_rank=training_args.local_rank, evaluate=True)
if training_args.do_eval
else None
)
data_collator = DataCollatorForLanguageModeling(
tokenizer=tokenizer, mlm=data_args.mlm, mlm_probability=data_args.mlm_probability
)
# Make sure checkpoint recovery and continous training works on GPU, probably we need to make sure to push all parameters to the gpu
# Solves bug in Trainer https://github.com/huggingface/transformers/issues/4240
# put in if needed
model.to(training_args.device)
# Initialize our Trainer
trainer = Trainer(
model=model,
args=training_args,
data_collator=data_collator,
train_dataset=train_dataset,
eval_dataset=eval_dataset
)
# Training
if training_args.do_train:
model_path = (
model_args.model_name_or_path
if model_args.model_name_or_path is not None and os.path.isdir(model_args.model_name_or_path)
else None
)
trainer.train(model_path=model_path)
trainer.save_model()
# For convenience, we also re-save the tokenizer to the same directory,
# so that you can share your model easily on huggingface.co/models =)
if trainer.is_world_process_zero():
tokenizer.save_pretrained(training_args.output_dir)
# Evaluation
results = {}
if training_args.do_eval and training_args.local_rank in [-1, 0]:
logger.info("*** Evaluate ***")
eval_output = trainer.evaluate()
perplexity = math.exp(eval_output["eval_loss"])
result = {"perplexity": perplexity}
output_eval_file = os.path.join(training_args.output_dir, "eval_results_lm.txt")
with open(output_eval_file, "w") as writer:
logger.info("***** Eval results *****")
for key in sorted(result.keys()):
logger.info(" %s = %s", key, str(result[key]))
writer.write("%s = %s\n" % (key, str(result[key])))
results.update(result)
print("end time: " + time.strftime('%d.%m %H:%M'))
return results
def _mp_fn(index):
# For xla_spawn (TPUs)
main()
if __name__ == "__main__":
main()