from collections import defaultdict
from contextlib import nullcontext
from types import MethodType
from typing import TYPE_CHECKING, Dict, Literal, Optional, Tuple, Union

import torch
from transformers import Trainer
from trl import DPOTrainer
from trl.trainer.utils import disable_dropout_in_model

from ...extras.constants import IGNORE_INDEX
from ..utils import create_custom_optimzer, create_custom_scheduler


if TYPE_CHECKING:
    from transformers import PreTrainedModel, ProcessorMixin

    from ...hparams import FinetuningArguments


class CustomDPOTrainer(DPOTrainer):
    def __init__(
        self,
        model: Union["PreTrainedModel", torch.nn.Module],
        ref_model: Optional[Union["PreTrainedModel", torch.nn.Module]],
        finetuning_args: "FinetuningArguments",
        processor: Optional["ProcessorMixin"],
        disable_dropout: bool = True,
        **kwargs,
    ):
        if disable_dropout:
            disable_dropout_in_model(model)
            if ref_model is not None:
                disable_dropout_in_model(ref_model)

        self.finetuning_args = finetuning_args
        self.processor = processor
        self.reference_free = False
        self.use_dpo_data_collator = True  # hack to avoid warning
        self.generate_during_eval = False  # disable at evaluation
        self.label_pad_token_id = IGNORE_INDEX
        self.padding_value = 0
        self.is_encoder_decoder = model.config.is_encoder_decoder
        self.precompute_ref_log_probs = False
        self._precomputed_train_ref_log_probs = False
        self._precomputed_eval_ref_log_probs = False
        self._peft_has_been_casted_to_bf16 = False

        self.ref_model = ref_model
        self._stored_metrics = defaultdict(lambda: defaultdict(list))

        # dpo hyperparams
        self.beta = finetuning_args.dpo_beta
        self.label_smoothing = finetuning_args.dpo_label_smoothing
        self.loss_type = finetuning_args.dpo_loss
        self.ftx_gamma = finetuning_args.dpo_ftx

        Trainer.__init__(self, model=model, **kwargs)
        if not hasattr(self, "accelerator"):
            raise AttributeError("Please update `transformers`.")

        if ref_model is not None:
            if self.is_deepspeed_enabled:
                if not (
                    getattr(ref_model, "is_loaded_in_8bit", False) or getattr(ref_model, "is_loaded_in_4bit", False)
                ):  # quantized models are already set on the correct device
                    self.ref_model = self._prepare_deepspeed(self.ref_model)
            else:
                self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)

        if finetuning_args.use_badam:
            from badam import clip_grad_norm_for_sparse_tensor

            self.accelerator.clip_grad_norm_ = MethodType(clip_grad_norm_for_sparse_tensor, self.accelerator)

    def create_optimizer(self) -> "torch.optim.Optimizer":
        if self.optimizer is None:
            self.optimizer = create_custom_optimzer(self.model, self.args, self.finetuning_args)
        return super().create_optimizer()

    def create_scheduler(
        self, num_training_steps: int, optimizer: Optional["torch.optim.Optimizer"] = None
    ) -> "torch.optim.lr_scheduler.LRScheduler":
        create_custom_scheduler(self.args, num_training_steps, optimizer)
        return super().create_scheduler(num_training_steps, optimizer)

    def _save(self, output_dir: Optional[str] = None, state_dict: Optional[Dict[str, "torch.Tensor"]] = None) -> None:
        super()._save(output_dir, state_dict)
        if self.processor is not None:
            output_dir = output_dir if output_dir is not None else self.args.output_dir
            getattr(self.processor, "image_processor").save_pretrained(output_dir)

    def sft_loss(self, chosen_logits: "torch.FloatTensor", chosen_labels: "torch.LongTensor") -> "torch.Tensor":
        r"""
        Computes supervised cross-entropy loss of given labels under the given logits.

        Returns:
            A tensor of shape (batch_size,) containing the cross-entropy loss of each samples.
        """
        all_logps = self.get_batch_logps(chosen_logits, chosen_labels, average_log_prob=True)
        return -all_logps

    def concatenated_forward(
        self, model: "PreTrainedModel", batch: Dict[str, "torch.Tensor"]
    ) -> Tuple["torch.Tensor", "torch.Tensor", "torch.Tensor", "torch.Tensor"]:
        r"""
        Computes the sum log probabilities of the labels under the given logits if loss_type != IPO.

        Otherwise the average log probabilities.
        """
        batch_copied = {k: v.detach().clone() for k, v in batch.items()}  # avoid error
        all_logits: "torch.Tensor" = model(**batch_copied, return_dict=True, use_cache=False).logits.to(torch.float32)

        all_logps = self.get_batch_logps(
            logits=all_logits,
            labels=batch_copied["labels"],
            average_log_prob=(self.loss_type == "ipo"),
            is_encoder_decoder=self.is_encoder_decoder,
            label_pad_token_id=self.label_pad_token_id,
        )
        batch_size = batch["input_ids"].size(0) // 2
        chosen_logps, rejected_logps = all_logps.split(batch_size, dim=0)
        chosen_logits, rejected_logits = all_logits.split(batch_size, dim=0)
        return chosen_logps, rejected_logps, chosen_logits, rejected_logits

    def get_batch_loss_metrics(
        self,
        model: "PreTrainedModel",
        batch: Dict[str, "torch.Tensor"],
        train_eval: Literal["train", "eval"] = "train",
    ) -> Tuple["torch.Tensor", Dict[str, "torch.Tensor"]]:
        r"""
        Computes the DPO loss and other metrics for the given batch of inputs for train or test.
        """
        metrics = {}
        (
            policy_chosen_logps,
            policy_rejected_logps,
            policy_chosen_logits,
            policy_rejected_logits,
        ) = self.concatenated_forward(model, batch)

        with torch.no_grad():
            if self.ref_model is None:
                ref_model = self.model
                ref_context = self.accelerator.unwrap_model(self.model).disable_adapter()
            else:
                ref_model = self.ref_model
                ref_context = nullcontext()

            with ref_context:
                (
                    reference_chosen_logps,
                    reference_rejected_logps,
                    _,
                    _,
                ) = self.concatenated_forward(ref_model, batch)

        losses, chosen_rewards, rejected_rewards = self.dpo_loss(
            policy_chosen_logps,
            policy_rejected_logps,
            reference_chosen_logps,
            reference_rejected_logps,
        )
        if self.ftx_gamma > 1e-6:
            batch_size = batch["input_ids"].size(0) // 2
            chosen_labels, _ = batch["labels"].split(batch_size, dim=0)
            losses += self.ftx_gamma * self.sft_loss(policy_chosen_logits, chosen_labels)

        reward_accuracies = (chosen_rewards > rejected_rewards).float()

        prefix = "eval_" if train_eval == "eval" else ""
        metrics["{}rewards/chosen".format(prefix)] = chosen_rewards.mean().cpu()
        metrics["{}rewards/rejected".format(prefix)] = rejected_rewards.mean().cpu()
        metrics["{}rewards/accuracies".format(prefix)] = reward_accuracies.mean().cpu()
        metrics["{}rewards/margins".format(prefix)] = (chosen_rewards - rejected_rewards).mean().cpu()
        metrics["{}logps/rejected".format(prefix)] = policy_rejected_logps.detach().mean().cpu()
        metrics["{}logps/chosen".format(prefix)] = policy_chosen_logps.detach().mean().cpu()
        metrics["{}logits/rejected".format(prefix)] = policy_rejected_logits.detach().mean().cpu()
        metrics["{}logits/chosen".format(prefix)] = policy_chosen_logits.detach().mean().cpu()

        return losses.mean(), metrics