run_nlu.py

#!/usr/bin/env python
# coding=utf-8
# Copyright 2020 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.
""" Finetuning the library models for sequence classification on GLUE."""
# You can also adapt this script on your own text classification task. Pointers for this are left as comments.

import logging
import os
import random
import sys
import re

import datasets
import numpy as np

import itertools
import evaluate
import transformers
from transformers import (
    AutoConfig,
    AutoModelForSequenceClassification,
    AutoTokenizer,
    DataCollatorWithPadding,
    EvalPrediction,
    HfArgumentParser,
    PretrainedConfig,
    TrainingArguments,
    default_data_collator,
    set_seed,
)
from transformers.trainer_utils import get_last_checkpoint
from transformers.utils import check_min_version, send_example_telemetry
from transformers.utils.versions import require_version
from sklearn.metrics import f1_score, accuracy_score, recall_score, precision_score

from src.loader.load_dataset_and_model import load_datasets
from src.utils.args_helper import DataTrainingArguments, ModelArguments
from src.trainer.trainer import get_trainer, get_compute_metrics

import torch
import torch.nn as nn

# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
# check_min_version("4.22.0.dev0")

require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")

logger = logging.getLogger(__name__)
    
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_glue", model_args, data_args)

    # 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}")

    # 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 and training_args.resume_from_checkpoint is 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."
            )

    # Set seed before initializing model.
    set_seed(training_args.seed)

    train_dataset, eval_dataset, model, tokenizer, \
        is_regression, is_multilabel = load_datasets(data_args, model_args, training_args)

    # Log a few random samples from the training set:
    # if training_args.do_train:
    #     for index in random.sample(range(len(train_dataset)), 3):
    #         logger.info(f"Sample {index} of the training set: {train_dataset[index]}.")
    #         logger.info(tokenizer.decode(train_dataset[index]['input_ids']))

    # Get the metric function
    # if data_args.task_name is not None and data_args.dataset_name is not "indonlu":
    #     metric = evaluate.load("glue", data_args.task_name)
#     else:
#         metric = evaluate.load("accuracy")

    # You can define your custom compute_metrics function. It takes an `EvalPrediction` object (a namedtuple with a
    # predictions and label_ids field) and has to return a dictionary string to float.

    # Data collator will default to DataCollatorWithPadding when the tokenizer is passed to Trainer, so we change it if
    # we already did the padding.
    if data_args.pad_to_max_length:
        data_collator = default_data_collator
    elif training_args.fp16:
        data_collator = DataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
    else:
        data_collator = None

    # Initialize our Trainer
    training_args.save_strategy="no"
    trainer = get_trainer(
        dataset_name=data_args.dataset_name,
        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,
        compute_metrics=get_compute_metrics(data_args.dataset_name),
        tokenizer=tokenizer,
        data_collator=data_collator
    )

    # Training
    if training_args.do_train:
        checkpoint = None
        if training_args.resume_from_checkpoint is not None:
            checkpoint = training_args.resume_from_checkpoint
        elif last_checkpoint is not None:
            checkpoint = last_checkpoint
        train_result = trainer.train(resume_from_checkpoint=checkpoint)
        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.save_model()  # Saves the tokenizer too for easy upload

        trainer.log_metrics("train", metrics)
        trainer.save_metrics("train", metrics)
        trainer.save_state()

    # Evaluation
    if training_args.do_eval:
        logger.info("*** Evaluate ***")

        # Loop to handle MNLI double evaluation (matched, mis-matched)
        tasks = [data_args.task_name]
        eval_datasets = [eval_dataset]
        if data_args.task_name == "mnli":
            tasks.append("mnli-mm")
            eval_datasets.append(raw_datasets["validation_mismatched"])
            combined = {}

        for eval_dataset, task in zip(eval_datasets, tasks):
            metrics = trainer.evaluate(eval_dataset=eval_dataset)

            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))

            if task == "mnli-mm":
                metrics = {k + "_mm": v for k, v in metrics.items()}
            if task is not None and "mnli" in task:
                combined.update(metrics)

            trainer.log_metrics("eval", metrics)
            trainer.save_metrics("eval", combined if task is not None and "mnli" in task else metrics)

    if training_args.do_predict:
        logger.info("*** Predict ***")

        # Loop to handle MNLI double evaluation (matched, mis-matched)
        tasks = [data_args.task_name]
        predict_datasets = [predict_dataset]
        if data_args.task_name == "mnli":
            tasks.append("mnli-mm")
            predict_datasets.append(raw_datasets["test_mismatched"])

        for predict_dataset, task in zip(predict_datasets, tasks):
            # Removing the `label` columns because it contains -1 and Trainer won't like that.
            predict_dataset = predict_dataset.remove_columns("label")
            predictions = trainer.predict(predict_dataset, metric_key_prefix="predict").predictions
            predictions = np.squeeze(predictions) if is_regression else np.argmax(predictions, axis=1)

            output_predict_file = os.path.join(training_args.output_dir, f"predict_results_{task}.txt")
            if trainer.is_world_process_zero():
                with open(output_predict_file, "w") as writer:
                    logger.info(f"***** Predict results {task} *****")
                    writer.write("index\tprediction\n")
                    for index, item in enumerate(predictions):
                        if is_regression:
                            writer.write(f"{index}\t{item:3.3f}\n")
                        else:
                            item = label_list[item]
                            writer.write(f"{index}\t{item}\n")

    kwargs = {"finetuned_from": model_args.model_name_or_path, "tasks": "text-classification"}
    if data_args.task_name is not None:
        kwargs["language"] = "en"
        kwargs["dataset_tags"] = data_args.dataset_name
        kwargs["dataset_args"] = data_args.task_name
        kwargs["dataset"] = f"{data_args.dataset_name.upper()} {data_args.task_name.upper()}"

    if training_args.push_to_hub:
        trainer.push_to_hub(**kwargs)
    else:
        trainer.create_model_card(**kwargs)


def _mp_fn(index):
    # For xla_spawn (TPUs)
    main()


if __name__ == "__main__":
    main()