# Copyright 2024 the LlamaFactory team.
#
# This code is inspired by the CarperAI's trlx library.
# https://github.com/CarperAI/trlx/blob/v0.7.0/examples/summarize_rlhf/reward_model/train_reward_model_gptj.py
#
# 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.
#
# MIT License
#
# Copyright (c) 2022 CarperAI
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

from typing import TYPE_CHECKING, List, Optional

from ...data import PairwiseDataCollatorWithPadding, get_dataset, split_dataset
from ...extras.callbacks import FixValueHeadModelCallback
from ...extras.misc import fix_valuehead_checkpoint
from ...extras.ploting import plot_loss
from ...model import load_model, load_tokenizer
from ..trainer_utils import create_modelcard_and_push
from .metric import compute_accuracy
from .trainer import PairwiseTrainer


if TYPE_CHECKING:
    from transformers import Seq2SeqTrainingArguments, TrainerCallback

    from ...hparams import DataArguments, FinetuningArguments, ModelArguments


def run_rm(
    model_args: "ModelArguments",
    data_args: "DataArguments",
    training_args: "Seq2SeqTrainingArguments",
    finetuning_args: "FinetuningArguments",
    callbacks: Optional[List["TrainerCallback"]] = None,
):
    tokenizer_module = load_tokenizer(model_args)
    tokenizer = tokenizer_module["tokenizer"]
    dataset = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
    model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
    data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)

    # Update arguments
    training_args.remove_unused_columns = False  # important for pairwise dataset

    # Initialize our Trainer
    trainer = PairwiseTrainer(
        model=model,
        args=training_args,
        finetuning_args=finetuning_args,
        data_collator=data_collator,
        callbacks=callbacks + [FixValueHeadModelCallback()],
        compute_metrics=compute_accuracy,
        **tokenizer_module,
        **split_dataset(dataset, data_args, training_args),
    )

    # Training
    if training_args.do_train:
        train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
        trainer.save_model()
        if training_args.should_save:
            fix_valuehead_checkpoint(model, training_args.output_dir, training_args.save_safetensors)
        trainer.log_metrics("train", train_result.metrics)
        trainer.save_metrics("train", train_result.metrics)
        trainer.save_state()
        if trainer.is_world_process_zero() and finetuning_args.plot_loss:
            plot_loss(training_args.output_dir, keys=["loss", "eval_loss", "eval_accuracy"])

    # Evaluation
    if training_args.do_eval:
        metrics = trainer.evaluate(metric_key_prefix="eval")
        trainer.log_metrics("eval", metrics)
        trainer.save_metrics("eval", metrics)

    # Predict
    if training_args.do_predict:
        predict_results = trainer.predict(dataset, metric_key_prefix="predict")
        trainer.log_metrics("predict", predict_results.metrics)
        trainer.save_metrics("predict", predict_results.metrics)
        trainer.save_predictions(predict_results)

    # Create model card
    create_modelcard_and_push(trainer, model_args, data_args, training_args, finetuning_args)