|
|
|
|
@@ -0,0 +1,945 @@
|
|
|
|
|
#!/usr/bin/env python
|
|
|
|
|
# coding=utf-8
|
|
|
|
|
# Copyright 2022 {{cookiecutter.authors}} and The HuggingFace Inc. team. 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 a 🤗 Transformers model on {{cookiecutter.example_name}}.
|
|
|
|
|
"""
|
|
|
|
|
# You can also adapt this script on your own {{cookiecutter.example_name}} task. Pointers for this are left as comments.
|
|
|
|
|
|
|
|
|
|
{%- if cookiecutter.with_trainer == "True" %}
|
|
|
|
|
|
|
|
|
|
import logging
|
|
|
|
|
import math
|
|
|
|
|
import os
|
|
|
|
|
import sys
|
|
|
|
|
from dataclasses import dataclass, field
|
|
|
|
|
from typing import Optional, List
|
|
|
|
|
|
|
|
|
|
import datasets
|
|
|
|
|
import torch
|
|
|
|
|
from datasets import load_dataset
|
|
|
|
|
|
|
|
|
|
import transformers
|
|
|
|
|
from transformers import (
|
|
|
|
|
CONFIG_MAPPING,
|
|
|
|
|
MODEL_MAPPING,
|
|
|
|
|
AutoConfig,
|
|
|
|
|
{{cookiecutter.model_class}},
|
|
|
|
|
AutoTokenizer,
|
|
|
|
|
DataCollatorWithPadding,
|
|
|
|
|
HfArgumentParser,
|
|
|
|
|
Trainer,
|
|
|
|
|
TrainingArguments,
|
|
|
|
|
default_data_collator,
|
|
|
|
|
set_seed,
|
|
|
|
|
)
|
|
|
|
|
from transformers.trainer_utils import get_last_checkpoint
|
|
|
|
|
from transformers.utils import send_example_telemetry
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
# You should update this to your particular problem to have better documentation of `model_type`
|
|
|
|
|
MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
|
|
|
|
|
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@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. "
|
|
|
|
|
"Don't set 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 huggingface.co"}
|
|
|
|
|
)
|
|
|
|
|
use_fast_tokenizer: bool = field(
|
|
|
|
|
default=True,
|
|
|
|
|
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
|
|
|
|
|
)
|
|
|
|
|
{%- elif cookiecutter.can_train_from_scratch == "False" %}
|
|
|
|
|
@dataclass
|
|
|
|
|
class ModelArguments:
|
|
|
|
|
"""
|
|
|
|
|
Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
model_name_or_path: str = field(
|
|
|
|
|
metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
|
|
|
|
|
)
|
|
|
|
|
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 huggingface.co"}
|
|
|
|
|
)
|
|
|
|
|
use_fast_tokenizer: bool = field(
|
|
|
|
|
default=True,
|
|
|
|
|
metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
|
|
|
|
|
)
|
|
|
|
|
model_revision: str = field(
|
|
|
|
|
default="main",
|
|
|
|
|
metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
|
|
|
|
|
)
|
|
|
|
|
token: str = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={
|
|
|
|
|
"help": (
|
|
|
|
|
"The token to use as HTTP bearer authorization for remote files. If not specified, will use the token "
|
|
|
|
|
"generated when running `hf auth login` (stored in `~/.huggingface`)."
|
|
|
|
|
)
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
trust_remote_code: bool = field(
|
|
|
|
|
default=False,
|
|
|
|
|
metadata={
|
|
|
|
|
"help": (
|
|
|
|
|
"Whether to trust the execution of code from datasets/models defined on the Hub."
|
|
|
|
|
" This option should only be set to `True` for repositories you trust and in which you have read the"
|
|
|
|
|
" code, as it will execute code present on the Hub on your local machine."
|
|
|
|
|
)
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@dataclass
|
|
|
|
|
class DataTrainingArguments:
|
|
|
|
|
"""
|
|
|
|
|
Arguments pertaining to what data we are going to input our model for training and eval.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
dataset_name: Optional[str] = field(
|
|
|
|
|
default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
|
|
|
|
|
)
|
|
|
|
|
dataset_config_name: Optional[str] = field(
|
|
|
|
|
default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
|
|
|
|
|
)
|
|
|
|
|
train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
|
|
|
|
|
validation_file: Optional[str] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
|
|
|
|
|
)
|
|
|
|
|
test_file: Optional[str] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={"help": "An optional input test data file to predict the label on (a text file)."},
|
|
|
|
|
)
|
|
|
|
|
overwrite_cache: bool = field(
|
|
|
|
|
default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
|
|
|
|
|
)
|
|
|
|
|
preprocessing_num_workers: Optional[int] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={"help": "The number of processes to use for the preprocessing."},
|
|
|
|
|
)
|
|
|
|
|
max_train_samples: Optional[int] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={
|
|
|
|
|
"help": "For debugging purposes or quicker training, truncate the number of training examples to this "
|
|
|
|
|
"value if set."
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
max_eval_samples: Optional[int] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={
|
|
|
|
|
"help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
|
|
|
|
|
"value if set."
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
max_predict_samples: Optional[int] = field(
|
|
|
|
|
default=None,
|
|
|
|
|
metadata={
|
|
|
|
|
"help": "For debugging purposes or quicker training, truncate the number of prediction examples to this "
|
|
|
|
|
"value if set."
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
def __post_init__(self):
|
|
|
|
|
if (
|
|
|
|
|
self.dataset_name is None
|
|
|
|
|
and self.train_file is None
|
|
|
|
|
and self.validation_file is None
|
|
|
|
|
and self.test_file is None
|
|
|
|
|
):
|
|
|
|
|
raise ValueError("Need either a dataset name or a training/validation/test file.")
|
|
|
|
|
else:
|
|
|
|
|
if self.train_file is not None:
|
|
|
|
|
extension = self.train_file.split(".")[-1]
|
|
|
|
|
assert extension in ["csv", "json", "txt"], "`train_file` should be a csv, a json or a txt file."
|
|
|
|
|
if self.validation_file is not None:
|
|
|
|
|
extension = self.validation_file.split(".")[-1]
|
|
|
|
|
assert extension in ["csv", "json", "txt"], "`validation_file` should be a csv, a json or a txt file."
|
|
|
|
|
if self.test_file is not None:
|
|
|
|
|
extension = self.test_file.split(".")[-1]
|
|
|
|
|
assert extension in ["csv", "json", "txt"], "`test_file` should be a csv, a json or a txt file."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
|
# 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))
|
|
|
|
|
if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
|
|
|
|
|
# If we pass only one argument to the script and it's the path to a json file,
|
|
|
|
|
# let's parse it to get our arguments.
|
|
|
|
|
model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
|
|
|
|
|
else:
|
|
|
|
|
model_args, data_args, training_args = parser.parse_args_into_dataclasses()
|
|
|
|
|
|
|
|
|
|
# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
|
|
|
|
|
# information sent is the one passed as arguments along with your Python/PyTorch versions.
|
|
|
|
|
send_example_telemetry("run_{{cookiecutter.example_shortcut}}", model_args, data_args)
|
|
|
|
|
|
|
|
|
|
# Detecting last checkpoint.
|
|
|
|
|
last_checkpoint = None
|
|
|
|
|
if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
|
|
|
|
|
last_checkpoint = get_last_checkpoint(training_args.output_dir)
|
|
|
|
|
if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
|
|
|
|
|
raise ValueError(
|
|
|
|
|
f"Output directory ({training_args.output_dir}) already exists and is not empty. "
|
|
|
|
|
"Use --overwrite_output_dir to overcome."
|
|
|
|
|
)
|
|
|
|
|
elif last_checkpoint is not None:
|
|
|
|
|
logger.info(
|
|
|
|
|
f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
|
|
|
|
|
"the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Setup logging
|
|
|
|
|
logging.basicConfig(
|
|
|
|
|
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
|
|
|
|
|
datefmt="%m/%d/%Y %H:%M:%S",
|
|
|
|
|
handlers=[logging.StreamHandler(sys.stdout)],
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
log_level = training_args.get_process_log_level()
|
|
|
|
|
logger.setLevel(log_level)
|
|
|
|
|
datasets.utils.logging.set_verbosity(log_level)
|
|
|
|
|
transformers.utils.logging.set_verbosity(log_level)
|
|
|
|
|
transformers.utils.logging.enable_default_handler()
|
|
|
|
|
transformers.utils.logging.enable_explicit_format()
|
|
|
|
|
|
|
|
|
|
# Log on each process the small summary:
|
|
|
|
|
logger.warning(
|
|
|
|
|
f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
|
|
|
|
|
+ f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
|
|
|
|
|
)
|
|
|
|
|
logger.info(f"Training/evaluation parameters {training_args}")
|
|
|
|
|
|
|
|
|
|
# Set seed before initializing model.
|
|
|
|
|
set_seed(training_args.seed)
|
|
|
|
|
|
|
|
|
|
# Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
|
|
|
|
|
# or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
|
|
|
|
|
# (the dataset will be downloaded automatically from the datasets Hub).
|
|
|
|
|
#
|
|
|
|
|
# For CSV/JSON files, this script will use the column called 'text' or the first column if no column called
|
|
|
|
|
# 'text' is found. You can easily tweak this behavior (see below).
|
|
|
|
|
#
|
|
|
|
|
# In distributed training, the load_dataset function guarantee that only one local process can concurrently
|
|
|
|
|
# download the dataset.
|
|
|
|
|
if data_args.dataset_name is not None:
|
|
|
|
|
# Downloading and loading a dataset from the hub.
|
|
|
|
|
raw_datasets = load_dataset(
|
|
|
|
|
data_args.dataset_name,
|
|
|
|
|
data_args.dataset_config_name,
|
|
|
|
|
trust_remote_code=model_args.trust_remote_code,
|
|
|
|
|
)
|
|
|
|
|
else:
|
|
|
|
|
data_files = {}
|
|
|
|
|
if data_args.train_file is not None:
|
|
|
|
|
data_files["train"] = data_args.train_file
|
|
|
|
|
extension = data_args.train_file.split(".")[-1]
|
|
|
|
|
if data_args.validation_file is not None:
|
|
|
|
|
data_files["validation"] = data_args.validation_file
|
|
|
|
|
extension = data_args.validation_file.split(".")[-1]
|
|
|
|
|
if data_args.test_file is not None:
|
|
|
|
|
data_files["test"] = data_args.test_file
|
|
|
|
|
extension = data_args.test_file.split(".")[-1]
|
|
|
|
|
if extension == "txt":
|
|
|
|
|
extension = "text"
|
|
|
|
|
raw_datasets = load_dataset(extension, data_files=data_files)
|
|
|
|
|
# See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
|
|
|
|
|
# https://huggingface.co/docs/datasets/loading_datasets.
|
|
|
|
|
|
|
|
|
|
# Load pretrained model and tokenizer
|
|
|
|
|
#
|
|
|
|
|
# Distributed training:
|
|
|
|
|
# The .from_pretrained methods guarantee that only one local process can concurrently
|
|
|
|
|
# download model & vocab.
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
config_kwargs = {
|
|
|
|
|
"cache_dir": model_args.cache_dir,
|
|
|
|
|
"revision": model_args.model_revision,
|
|
|
|
|
"token": model_args.token,
|
|
|
|
|
"trust_remote_code": model_args.trust_remote_code,
|
|
|
|
|
}
|
|
|
|
|
if model_args.config_name:
|
|
|
|
|
config = AutoConfig.from_pretrained(model_args.config_name, **config_kwargs)
|
|
|
|
|
elif model_args.model_name_or_path:
|
|
|
|
|
config = AutoConfig.from_pretrained(model_args.model_name_or_path, **config_kwargs)
|
|
|
|
|
else:
|
|
|
|
|
config = CONFIG_MAPPING[model_args.model_type]()
|
|
|
|
|
logger.warning("You are instantiating a new config instance from scratch.")
|
|
|
|
|
|
|
|
|
|
tokenizer_kwargs = {
|
|
|
|
|
"cache_dir": model_args.cache_dir,
|
|
|
|
|
"use_fast": model_args.use_fast_tokenizer,
|
|
|
|
|
"revision": model_args.model_revision,
|
|
|
|
|
"token": model_args.token,
|
|
|
|
|
"trust_remote_code": model_args.trust_remote_code,
|
|
|
|
|
}
|
|
|
|
|
if model_args.tokenizer_name:
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, **tokenizer_kwargs)
|
|
|
|
|
elif model_args.model_name_or_path:
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, **tokenizer_kwargs)
|
|
|
|
|
else:
|
|
|
|
|
raise ValueError(
|
|
|
|
|
"You are instantiating a new tokenizer from scratch. This is not supported by this script. "
|
|
|
|
|
"You can do it from another script, save it, and load it from here, using --tokenizer_name."
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if model_args.model_name_or_path:
|
|
|
|
|
model = {{cookiecutter.model_class}}.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,
|
|
|
|
|
revision=model_args.model_revision,
|
|
|
|
|
token=model_args.token,
|
|
|
|
|
trust_remote_code=model_args.trust_remote_code,
|
|
|
|
|
)
|
|
|
|
|
else:
|
|
|
|
|
logger.info("Training new model from scratch")
|
|
|
|
|
model = {{cookiecutter.model_class}}.from_config(config)
|
|
|
|
|
|
|
|
|
|
model.resize_token_embeddings(len(tokenizer))
|
|
|
|
|
{%- elif cookiecutter.can_train_from_scratch == "False" %}
|
|
|
|
|
config = AutoConfig.from_pretrained(
|
|
|
|
|
model_args.config_name if model_args.config_name else model_args.model_name_or_path,
|
|
|
|
|
# num_labels=num_labels, Uncomment if you have a certain number of labels
|
|
|
|
|
finetuning_task=data_args.task_name,
|
|
|
|
|
cache_dir=model_args.cache_dir,
|
|
|
|
|
revision=model_args.model_revision,
|
|
|
|
|
token=model_args.token,
|
|
|
|
|
trust_remote_code=model_args.trust_remote_code,
|
|
|
|
|
)
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
|
|
|
model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
|
|
|
|
|
cache_dir=model_args.cache_dir,
|
|
|
|
|
use_fast=model_args.use_fast_tokenizer,
|
|
|
|
|
revision=model_args.model_revision,
|
|
|
|
|
token=model_args.token,
|
|
|
|
|
trust_remote_code=model_args.trust_remote_code,
|
|
|
|
|
)
|
|
|
|
|
model = AutoModelForSequenceClassification.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,
|
|
|
|
|
revision=model_args.model_revision,
|
|
|
|
|
token=model_args.token,
|
|
|
|
|
trust_remote_code=model_args.trust_remote_code,
|
|
|
|
|
)
|
|
|
|
|
{% endif %}
|
|
|
|
|
|
|
|
|
|
# Preprocessing the datasets.
|
|
|
|
|
# First we tokenize all the texts.
|
|
|
|
|
if training_args.do_train:
|
|
|
|
|
column_names = raw_datasets["train"].column_names
|
|
|
|
|
elif training_args.do_eval:
|
|
|
|
|
column_names = raw_datasets["validation"].column_names
|
|
|
|
|
elif training_args.do_predict:
|
|
|
|
|
column_names = raw_datasets["test"].column_names
|
|
|
|
|
text_column_name = "text" if "text" in column_names else column_names[0]
|
|
|
|
|
|
|
|
|
|
def tokenize_function(examples):
|
|
|
|
|
return tokenizer(examples[text_column_name], padding="max_length", truncation=True)
|
|
|
|
|
|
|
|
|
|
if training_args.do_train:
|
|
|
|
|
if "train" not in raw_datasets:
|
|
|
|
|
raise ValueError("--do_train requires a train dataset")
|
|
|
|
|
train_dataset = raw_datasets["train"]
|
|
|
|
|
if data_args.max_train_samples is not None:
|
|
|
|
|
# Select Sample from Dataset
|
|
|
|
|
train_dataset = train_dataset.select(range(data_args.max_train_samples))
|
|
|
|
|
# tokenize train dataset in batch
|
|
|
|
|
with training_args.main_process_first(desc="train dataset map tokenization"):
|
|
|
|
|
train_dataset = train_dataset.map(
|
|
|
|
|
tokenize_function,
|
|
|
|
|
batched=True,
|
|
|
|
|
num_proc=data_args.preprocessing_num_workers,
|
|
|
|
|
remove_columns=[text_column_name],
|
|
|
|
|
load_from_cache_file=not data_args.overwrite_cache,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if training_args.do_eval:
|
|
|
|
|
if "validation" not in raw_datasets:
|
|
|
|
|
raise ValueError("--do_eval requires a validation dataset")
|
|
|
|
|
eval_dataset = raw_datasets["validation"]
|
|
|
|
|
# Selecting samples from dataset
|
|
|
|
|
if data_args.max_eval_samples is not None:
|
|
|
|
|
eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
|
|
|
|
|
# tokenize validation dataset
|
|
|
|
|
with training_args.main_process_first(desc="validation dataset map tokenization"):
|
|
|
|
|
eval_dataset = eval_dataset.map(
|
|
|
|
|
tokenize_function,
|
|
|
|
|
batched=True,
|
|
|
|
|
num_proc=data_args.preprocessing_num_workers,
|
|
|
|
|
remove_columns=[text_column_name],
|
|
|
|
|
load_from_cache_file=not data_args.overwrite_cache,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if training_args.do_predict:
|
|
|
|
|
if "test" not in raw_datasets:
|
|
|
|
|
raise ValueError("--do_predict requires a test dataset")
|
|
|
|
|
predict_dataset = raw_datasets["test"]
|
|
|
|
|
# Selecting samples from dataset
|
|
|
|
|
if data_args.max_predict_samples is not None:
|
|
|
|
|
predict_dataset = predict_dataset.select(range(data_args.max_predict_samples))
|
|
|
|
|
# tokenize predict dataset
|
|
|
|
|
with training_args.main_process_first(desc="prediction dataset map tokenization"):
|
|
|
|
|
predict_dataset = predict_dataset.map(
|
|
|
|
|
tokenize_function,
|
|
|
|
|
batched=True,
|
|
|
|
|
num_proc=data_args.preprocessing_num_workers,
|
|
|
|
|
remove_columns=[text_column_name],
|
|
|
|
|
load_from_cache_file=not data_args.overwrite_cache,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Data collator
|
|
|
|
|
data_collator=default_data_collator if not training_args.fp16 else DataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
|
|
|
|
|
|
|
|
|
|
# Initialize our Trainer
|
|
|
|
|
trainer = Trainer(
|
|
|
|
|
model=model,
|
|
|
|
|
args=training_args,
|
|
|
|
|
train_dataset=train_dataset if training_args.do_train else None,
|
|
|
|
|
eval_dataset=eval_dataset if training_args.do_eval else None,
|
|
|
|
|
processing_class=tokenizer,
|
|
|
|
|
data_collator=data_collator,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Training
|
|
|
|
|
if training_args.do_train:
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "False" %}
|
|
|
|
|
if last_checkpoint is not None:
|
|
|
|
|
checkpoint = last_checkpoint
|
|
|
|
|
elif os.path.isdir(model_args.model_name_or_path):
|
|
|
|
|
checkpoint = model_args.model_name_or_path
|
|
|
|
|
else:
|
|
|
|
|
checkpoint = None
|
|
|
|
|
{%- elif cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
if last_checkpoint is not None:
|
|
|
|
|
checkpoint = last_checkpoint
|
|
|
|
|
elif model_args.model_name_or_path is not None and os.path.isdir(model_args.model_name_or_path):
|
|
|
|
|
checkpoint = model_args.model_name_or_path
|
|
|
|
|
else:
|
|
|
|
|
checkpoint = None
|
|
|
|
|
{% endif %}
|
|
|
|
|
train_result = trainer.train(resume_from_checkpoint=checkpoint)
|
|
|
|
|
trainer.save_model() # Saves the tokenizer too for easy upload
|
|
|
|
|
|
|
|
|
|
metrics = train_result.metrics
|
|
|
|
|
max_train_samples = (
|
|
|
|
|
data_args.max_train_samples if data_args.max_train_samples is not None else len(train_dataset)
|
|
|
|
|
)
|
|
|
|
|
metrics["train_samples"] = min(max_train_samples, len(train_dataset))
|
|
|
|
|
|
|
|
|
|
trainer.log_metrics("train", metrics)
|
|
|
|
|
trainer.save_metrics("train", metrics)
|
|
|
|
|
trainer.save_state()
|
|
|
|
|
|
|
|
|
|
# Evaluation
|
|
|
|
|
if training_args.do_eval:
|
|
|
|
|
logger.info("*** Evaluate ***")
|
|
|
|
|
|
|
|
|
|
metrics = trainer.evaluate()
|
|
|
|
|
|
|
|
|
|
max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
|
|
|
|
|
metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
|
|
|
|
|
|
|
|
|
|
trainer.log_metrics("eval", metrics)
|
|
|
|
|
trainer.save_metrics("eval", metrics)
|
|
|
|
|
|
|
|
|
|
# Prediction
|
|
|
|
|
if training_args.do_predict:
|
|
|
|
|
logger.info("*** Predict ***")
|
|
|
|
|
predictions, labels, metrics = trainer.predict(predict_dataset)
|
|
|
|
|
|
|
|
|
|
max_predict_samples = data_args.max_predict_samples if data_args.max_predict_samples is not None else len(predict_dataset)
|
|
|
|
|
metrics["predict_samples"] = min(max_predict_samples, len(predict_dataset))
|
|
|
|
|
|
|
|
|
|
trainer.log_metrics("predict", metrics)
|
|
|
|
|
trainer.save_metrics("predict", metrics)
|
|
|
|
|
|
|
|
|
|
# write custom code for saving predictions according to task
|
|
|
|
|
|
|
|
|
|
def _mp_fn(index):
|
|
|
|
|
# For xla_spawn (TPUs)
|
|
|
|
|
main()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
main()
|
|
|
|
|
|
|
|
|
|
{%- elif cookiecutter.with_trainer == "False" %}
|
|
|
|
|
|
|
|
|
|
import argparse
|
|
|
|
|
import logging
|
|
|
|
|
import math
|
|
|
|
|
import os
|
|
|
|
|
import random
|
|
|
|
|
|
|
|
|
|
import datasets
|
|
|
|
|
from datasets import load_dataset, load_metric
|
|
|
|
|
from torch.utils.data import DataLoader
|
|
|
|
|
from tqdm.auto import tqdm
|
|
|
|
|
|
|
|
|
|
import transformers
|
|
|
|
|
from accelerate import Accelerator
|
|
|
|
|
from transformers import (
|
|
|
|
|
CONFIG_MAPPING,
|
|
|
|
|
MODEL_MAPPING,
|
|
|
|
|
AutoConfig,
|
|
|
|
|
{{cookiecutter.model_class}},
|
|
|
|
|
AutoTokenizer,
|
|
|
|
|
DataCollatorWithPadding,
|
|
|
|
|
PretrainedConfig,
|
|
|
|
|
SchedulerType,
|
|
|
|
|
default_data_collator,
|
|
|
|
|
get_scheduler,
|
|
|
|
|
set_seed,
|
|
|
|
|
)
|
|
|
|
|
from transformers.utils import send_example_telemetry
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
# You should update this to your particular problem to have better documentation of `model_type`
|
|
|
|
|
MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
|
|
|
|
|
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
|
|
|
|
|
{% endif %}
|
|
|
|
|
|
|
|
|
|
def parse_args():
|
|
|
|
|
parser = argparse.ArgumentParser(description="Finetune a transformers model on a text classification task")
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--dataset_name",
|
|
|
|
|
type=str,
|
|
|
|
|
default=None,
|
|
|
|
|
help="The name of the dataset to use (via the datasets library).",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--dataset_config_name",
|
|
|
|
|
type=str,
|
|
|
|
|
default=None,
|
|
|
|
|
help= "The configuration name of the dataset to use (via the datasets library).",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--trust_remote_code",
|
|
|
|
|
action="store_true",
|
|
|
|
|
help=(
|
|
|
|
|
"Whether to trust the execution of code from datasets/models defined on the Hub."
|
|
|
|
|
" This option should only be set to `True` for repositories you trust and in which you have read the"
|
|
|
|
|
" code, as it will execute code present on the Hub on your local machine."
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--train_file", type=str, default=None, help="A csv or a json file containing the training data."
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--validation_file", type=str, default=None, help="A csv or a json file containing the validation data."
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--max_length",
|
|
|
|
|
type=int,
|
|
|
|
|
default=128,
|
|
|
|
|
help=(
|
|
|
|
|
"The maximum total input sequence length after tokenization. Sequences longer than this will be truncated,"
|
|
|
|
|
" sequences shorter will be padded if `--pad_to_max_length` is passed."
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--pad_to_max_length",
|
|
|
|
|
action="store_true",
|
|
|
|
|
help="If passed, pad all samples to `max_length`. Otherwise, dynamic padding is used.",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--model_name_or_path",
|
|
|
|
|
type=str,
|
|
|
|
|
help="Path to pretrained model or model identifier from huggingface.co/models.",
|
|
|
|
|
required=True,
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--config_name",
|
|
|
|
|
type=str,
|
|
|
|
|
default=None,
|
|
|
|
|
help="Pretrained config name or path if not the same as model_name",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--tokenizer_name",
|
|
|
|
|
type=str,
|
|
|
|
|
default=None,
|
|
|
|
|
help="Pretrained tokenizer name or path if not the same as model_name",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--use_slow_tokenizer",
|
|
|
|
|
action="store_true",
|
|
|
|
|
help="If passed, will use a slow tokenizer (not backed by the 🤗 Tokenizers library).",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--per_device_train_batch_size",
|
|
|
|
|
type=int,
|
|
|
|
|
default=8,
|
|
|
|
|
help="Batch size (per device) for the training dataloader.",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--per_device_eval_batch_size",
|
|
|
|
|
type=int,
|
|
|
|
|
default=8,
|
|
|
|
|
help="Batch size (per device) for the evaluation dataloader.",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--learning_rate",
|
|
|
|
|
type=float,
|
|
|
|
|
default=5e-5,
|
|
|
|
|
help="Initial learning rate (after the potential warmup period) to use.",
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument("--weight_decay", type=float, default=0.0, help="Weight decay to use.")
|
|
|
|
|
parser.add_argument("--num_train_epochs", type=int, default=3, help="Total number of training epochs to perform.")
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--max_train_steps",
|
|
|
|
|
type=int,
|
|
|
|
|
default=None,
|
|
|
|
|
help="Total number of training steps to perform. If provided, overrides num_train_epochs.",
|
|
|
|
|
)
|
|
|
|
|
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(
|
|
|
|
|
"--lr_scheduler_type",
|
|
|
|
|
type=SchedulerType,
|
|
|
|
|
default="linear",
|
|
|
|
|
help="The scheduler type to use.",
|
|
|
|
|
choices=["linear", "cosine", "cosine_with_restarts", "polynomial", "constant", "constant_with_warmup"],
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--num_warmup_steps", type=int, default=0, help="Number of steps for the warmup in the lr scheduler."
|
|
|
|
|
)
|
|
|
|
|
parser.add_argument("--output_dir", type=str, default=None, help="Where to store the final model.")
|
|
|
|
|
parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
parser.add_argument(
|
|
|
|
|
"--model_type",
|
|
|
|
|
type=str,
|
|
|
|
|
default=None,
|
|
|
|
|
help="Model type to use if training from scratch.",
|
|
|
|
|
choices=MODEL_TYPES,
|
|
|
|
|
)
|
|
|
|
|
{% endif %}
|
|
|
|
|
args = parser.parse_args()
|
|
|
|
|
|
|
|
|
|
# Sanity checks
|
|
|
|
|
if args.task_name is None and args.train_file is None and args.validation_file is None:
|
|
|
|
|
raise ValueError("Need either a task name or a training/validation file.")
|
|
|
|
|
else:
|
|
|
|
|
if args.train_file is not None:
|
|
|
|
|
extension = args.train_file.split(".")[-1]
|
|
|
|
|
assert extension in ["csv", "json"], "`train_file` should be a csv or a json file."
|
|
|
|
|
if args.validation_file is not None:
|
|
|
|
|
extension = args.validation_file.split(".")[-1]
|
|
|
|
|
assert extension in ["csv", "json"], "`validation_file` should be a csv or a json file."
|
|
|
|
|
|
|
|
|
|
if args.output_dir is not None:
|
|
|
|
|
os.makedirs(args.output_dir, exist_ok=True)
|
|
|
|
|
|
|
|
|
|
return args
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
|
args = parse_args()
|
|
|
|
|
|
|
|
|
|
# Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
|
|
|
|
|
# information sent is the one passed as arguments along with your Python/PyTorch versions.
|
|
|
|
|
send_example_telemetry("run_{{cookiecutter.example_shortcut}", args)
|
|
|
|
|
|
|
|
|
|
# Initialize the accelerator. We will let the accelerator handle device placement for us in this example.
|
|
|
|
|
accelerator = Accelerator()
|
|
|
|
|
# Make one log on every process with the configuration for debugging.
|
|
|
|
|
logging.basicConfig(
|
|
|
|
|
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
|
|
|
|
|
datefmt="%m/%d/%Y %H:%M:%S",
|
|
|
|
|
level=logging.INFO,
|
|
|
|
|
)
|
|
|
|
|
logger.info(accelerator.state)
|
|
|
|
|
|
|
|
|
|
# Setup logging, we only want one process per machine to log things on the screen.
|
|
|
|
|
# accelerator.is_local_main_process is only True for one process per machine.
|
|
|
|
|
logger.setLevel(logging.INFO if accelerator.is_local_main_process else logging.ERROR)
|
|
|
|
|
if accelerator.is_local_main_process:
|
|
|
|
|
datasets.utils.logging.set_verbosity_warning()
|
|
|
|
|
transformers.utils.logging.set_verbosity_info()
|
|
|
|
|
else:
|
|
|
|
|
datasets.utils.logging.set_verbosity_error()
|
|
|
|
|
transformers.utils.logging.set_verbosity_error()
|
|
|
|
|
|
|
|
|
|
# If passed along, set the training seed now.
|
|
|
|
|
if args.seed is not None:
|
|
|
|
|
set_seed(args.seed)
|
|
|
|
|
|
|
|
|
|
# Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
|
|
|
|
|
# or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
|
|
|
|
|
# (the dataset will be downloaded automatically from the datasets Hub).
|
|
|
|
|
#
|
|
|
|
|
# For CSV/JSON files, this script will use the column called 'text' or the first column if no column called
|
|
|
|
|
# 'text' is found. You can easily tweak this behavior (see below).
|
|
|
|
|
#
|
|
|
|
|
# In distributed training, the load_dataset function guarantee that only one local process can concurrently
|
|
|
|
|
# download the dataset.
|
|
|
|
|
if args.dataset_name is not None:
|
|
|
|
|
# Downloading and loading a dataset from the hub.
|
|
|
|
|
raw_datasets = load_dataset(
|
|
|
|
|
args.dataset_name, args.dataset_config_name, trust_remote_code=args.trust_remote_code
|
|
|
|
|
)
|
|
|
|
|
else:
|
|
|
|
|
data_files = {}
|
|
|
|
|
if args.train_file is not None:
|
|
|
|
|
data_files["train"] = args.train_file
|
|
|
|
|
extension = args.train_file.split(".")[-1]
|
|
|
|
|
if args.validation_file is not None:
|
|
|
|
|
data_files["validation"] = args.validation_file
|
|
|
|
|
extension = args.validation_file.split(".")[-1]
|
|
|
|
|
raw_datasets = load_dataset(extension, data_files=data_files)
|
|
|
|
|
# See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
|
|
|
|
|
# https://huggingface.co/docs/datasets/loading_datasets.
|
|
|
|
|
|
|
|
|
|
# Load pretrained model and tokenizer
|
|
|
|
|
#
|
|
|
|
|
# In distributed training, the .from_pretrained methods guarantee that only one local process can concurrently
|
|
|
|
|
# download model & vocab.
|
|
|
|
|
{%- if cookiecutter.can_train_from_scratch == "True" %}
|
|
|
|
|
if model_args.config_name:
|
|
|
|
|
config = AutoConfig.from_pretrained(args.model_name_or_path)
|
|
|
|
|
elif model_args.model_name_or_path:
|
|
|
|
|
config = AutoConfig.from_pretrained(args.model_name_or_path)
|
|
|
|
|
else:
|
|
|
|
|
config = CONFIG_MAPPING[args.model_type]()
|
|
|
|
|
logger.warning("You are instantiating a new config instance from scratch.")
|
|
|
|
|
|
|
|
|
|
if model_args.tokenizer_name:
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_args.tokenizer_name, use_fast=not args.use_slow_tokenizer)
|
|
|
|
|
elif model_args.model_name_or_path:
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_args.model_name_or_path, use_fast=not args.use_slow_tokenizer)
|
|
|
|
|
else:
|
|
|
|
|
raise ValueError(
|
|
|
|
|
"You are instantiating a new tokenizer from scratch. This is not supported by this script. "
|
|
|
|
|
"You can do it from another script, save it, and load it from here, using --tokenizer_name."
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
if model_args.model_name_or_path:
|
|
|
|
|
model = {{cookiecutter.model_class}}.from_pretrained(
|
|
|
|
|
model_args.model_name_or_path,
|
|
|
|
|
from_tf=bool(".ckpt" in model_args.model_name_or_path),
|
|
|
|
|
config=config,
|
|
|
|
|
)
|
|
|
|
|
else:
|
|
|
|
|
logger.info("Training new model from scratch")
|
|
|
|
|
model = {{cookiecutter.model_class}}.from_config(config)
|
|
|
|
|
|
|
|
|
|
model.resize_token_embeddings(len(tokenizer))
|
|
|
|
|
{%- elif cookiecutter.can_train_from_scratch == "False" %}
|
|
|
|
|
config = AutoConfig.from_pretrained(
|
|
|
|
|
args.config_name if model_args.config_name else args.model_name_or_path,
|
|
|
|
|
# num_labels=num_labels, Uncomment if you have a certain number of labels
|
|
|
|
|
finetuning_task=data_args.task_name,
|
|
|
|
|
)
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
|
|
|
args.tokenizer_name if model_args.tokenizer_name else args.model_name_or_path,
|
|
|
|
|
use_fast=not args.use_slow_tokenizer,
|
|
|
|
|
)
|
|
|
|
|
model = AutoModelForSequenceClassification.from_pretrained(
|
|
|
|
|
model_args.model_name_or_path,
|
|
|
|
|
from_tf=bool(".ckpt" in model_args.model_name_or_path),
|
|
|
|
|
config=config,
|
|
|
|
|
)
|
|
|
|
|
{% endif %}
|
|
|
|
|
|
|
|
|
|
# Preprocessing the datasets.
|
|
|
|
|
# First we tokenize all the texts.
|
|
|
|
|
column_names = raw_datasets["train"].column_names
|
|
|
|
|
text_column_name = "text" if "text" in column_names else column_names[0]
|
|
|
|
|
|
|
|
|
|
padding = "max_length" if args.pad_to_max_length else False
|
|
|
|
|
def tokenize_function(examples):
|
|
|
|
|
result = tokenizer(examples[text_column_name], padding=padding, max_length=args.max_length, truncation=True)
|
|
|
|
|
if "label" in examples:
|
|
|
|
|
result["labels"] = examples["label"]
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
processed_datasets = raw_datasets.map(
|
|
|
|
|
preprocess_function, batched=True, remove_columns=raw_datasets["train"].column_names
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
train_dataset = processed_datasets["train"]
|
|
|
|
|
eval_dataset = processed_datasets["validation"]
|
|
|
|
|
|
|
|
|
|
# Log a few random samples from the training set:
|
|
|
|
|
for index in random.sample(range(len(train_dataset)), 3):
|
|
|
|
|
logger.info(f"Sample {index} of the training set: {train_dataset[index]}.")
|
|
|
|
|
|
|
|
|
|
# DataLoaders creation:
|
|
|
|
|
if args.pad_to_max_length:
|
|
|
|
|
# If padding was already done ot max length, we use the default data collator that will just convert everything
|
|
|
|
|
# to tensors.
|
|
|
|
|
data_collator = default_data_collator
|
|
|
|
|
else:
|
|
|
|
|
# Otherwise, `DataCollatorWithPadding` will apply dynamic padding for us (by padding to the maximum length of
|
|
|
|
|
# the samples passed). When using mixed precision, we add `pad_to_multiple_of=8` to pad all tensors to multiple
|
|
|
|
|
# of 8s, which will enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta).
|
|
|
|
|
# For fp8, we pad to multiple of 16.
|
|
|
|
|
if accelerator.mixed_precision == "fp8":
|
|
|
|
|
pad_to_multiple_of = 16
|
|
|
|
|
elif accelerator.mixed_precision != "no":
|
|
|
|
|
pad_to_multiple_of = 8
|
|
|
|
|
else:
|
|
|
|
|
pad_to_multiple_of = None
|
|
|
|
|
data_collator = DataCollatorWithPadding(tokenizer, pad_to_multiple_of=pad_to_multiple_of)
|
|
|
|
|
|
|
|
|
|
train_dataloader = DataLoader(
|
|
|
|
|
train_dataset, shuffle=True, collate_fn=data_collator, batch_size=args.per_device_train_batch_size
|
|
|
|
|
)
|
|
|
|
|
eval_dataloader = DataLoader(eval_dataset, collate_fn=data_collator, batch_size=args.per_device_eval_batch_size)
|
|
|
|
|
|
|
|
|
|
# Optimizer
|
|
|
|
|
# Split weights in two groups, one with weight decay and the other not.
|
|
|
|
|
no_decay = ["bias", "LayerNorm.weight"]
|
|
|
|
|
optimizer_grouped_parameters = [
|
|
|
|
|
{
|
|
|
|
|
"params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)],
|
|
|
|
|
"weight_decay": args.weight_decay,
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)],
|
|
|
|
|
"weight_decay": 0.0,
|
|
|
|
|
},
|
|
|
|
|
]
|
|
|
|
|
optimizer = torch.optim.AdamW(optimizer_grouped_parameters, lr=args.learning_rate)
|
|
|
|
|
|
|
|
|
|
# Prepare everything with our `accelerator`.
|
|
|
|
|
model, optimizer, train_dataloader, eval_dataloader = accelerator.prepare(
|
|
|
|
|
model, optimizer, train_dataloader, eval_dataloader
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# Note -> the training dataloader needs to be prepared before we grab his length below (cause its length will be
|
|
|
|
|
# shorter in multiprocess)
|
|
|
|
|
|
|
|
|
|
# Scheduler and math around the number of training steps.
|
|
|
|
|
num_update_steps_per_epoch = math.ceil(len(train_dataloader) / args.gradient_accumulation_steps)
|
|
|
|
|
if args.max_train_steps is None:
|
|
|
|
|
args.max_train_steps = args.num_train_epochs * num_update_steps_per_epoch
|
|
|
|
|
else:
|
|
|
|
|
args.num_train_epochs = math.ceil(args.max_train_steps / num_update_steps_per_epoch)
|
|
|
|
|
|
|
|
|
|
lr_scheduler = get_scheduler(
|
|
|
|
|
name=args.lr_scheduler_type,
|
|
|
|
|
optimizer=optimizer,
|
|
|
|
|
num_warmup_steps=args.num_warmup_steps,
|
|
|
|
|
num_training_steps=args.max_train_steps,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# TODO Get the proper metric function
|
|
|
|
|
# metric = load_metric(xxx)
|
|
|
|
|
|
|
|
|
|
# Train!
|
|
|
|
|
total_batch_size = args.per_device_train_batch_size * accelerator.num_processes * args.gradient_accumulation_steps
|
|
|
|
|
|
|
|
|
|
logger.info("***** Running training *****")
|
|
|
|
|
logger.info(f" Num examples = {len(train_dataset)}")
|
|
|
|
|
logger.info(f" Num Epochs = {args.num_train_epochs}")
|
|
|
|
|
logger.info(f" Instantaneous batch size per device = {args.per_device_train_batch_size}")
|
|
|
|
|
logger.info(f" Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}")
|
|
|
|
|
logger.info(f" Gradient Accumulation steps = {args.gradient_accumulation_steps}")
|
|
|
|
|
logger.info(f" Total optimization steps = {args.max_train_steps}")
|
|
|
|
|
# Only show the progress bar once on each machine.
|
|
|
|
|
progress_bar = tqdm(range(args.max_train_steps), disable=not accelerator.is_local_main_process)
|
|
|
|
|
completed_steps = 0
|
|
|
|
|
|
|
|
|
|
for epoch in range(args.num_train_epochs):
|
|
|
|
|
model.train()
|
|
|
|
|
for step, batch in enumerate(train_dataloader):
|
|
|
|
|
outputs = model(**batch)
|
|
|
|
|
loss = outputs.loss
|
|
|
|
|
loss = loss / args.gradient_accumulation_steps
|
|
|
|
|
accelerator.backward(loss)
|
|
|
|
|
if step % args.gradient_accumulation_steps == 0 or step == len(train_dataloader) - 1:
|
|
|
|
|
optimizer.step()
|
|
|
|
|
lr_scheduler.step()
|
|
|
|
|
optimizer.zero_grad()
|
|
|
|
|
progress_bar.update(1)
|
|
|
|
|
completed_steps += 1
|
|
|
|
|
|
|
|
|
|
if completed_steps >= args.max_train_steps:
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
model.eval()
|
|
|
|
|
for step, batch in enumerate(eval_dataloader):
|
|
|
|
|
with torch.no_grad():
|
|
|
|
|
outputs = model(**batch)
|
|
|
|
|
predictions = outputs.logits.argmax(dim=-1)
|
|
|
|
|
metric.add_batch(
|
|
|
|
|
predictions=accelerator.gather(predictions),
|
|
|
|
|
references=accelerator.gather(batch["labels"]),
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
eval_metric = metric.compute()
|
|
|
|
|
logger.info(f"epoch {epoch}: {eval_metric}")
|
|
|
|
|
|
|
|
|
|
if args.output_dir is not None:
|
|
|
|
|
accelerator.wait_for_everyone()
|
|
|
|
|
unwrapped_model = accelerator.unwrap_model(model)
|
|
|
|
|
unwrapped_model.save_pretrained(args.output_dir, save_function=accelerator.save)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
main()
|
|
|
|
|
|
|
|
|
|
{% endif %}
|
