unsloth_compiled_cache/UnslothGRPOTrainer.py

"""
2025.7.7
2025.7.5
4.53.2
0.19.1
__UNSLOTH_VERSIONING__
"""
from torch import Tensor
import torch
import torch.nn as nn
from torch.nn import functional as F
from typing import Any, List, Optional, Tuple, Union, Dict, Set, Callable
from trl.trainer.grpo_trainer import (Any, AutoModelForCausalLM, AutoModelForSequenceClassification, AutoTokenizer, DataLoader, Dataset, FSDP, GRPOConfig, GRPOTrainer, GenerationConfig, IterableDataset, Optional, Path, PeftConfig, PreTrainedModel, PreTrainedTokenizerBase, RepeatSampler, RewardFunc, Sampler, SyncRefModelCallback, Trainer, TrainerCallback, Union, VLLMClient, _ForwardRedirection, apply_chat_template, broadcast_object_list, datasets, defaultdict, deque, disable_dropout_in_model, gather, gather_object, generate_model_card, get_comet_experiment_url, identity, is_conversational, is_datasets_available, is_liger_kernel_available, is_peft_available, is_peft_model, is_rich_available, is_vllm_available, is_wandb_available, maybe_apply_chat_template, nanmax, nanmin, nanstd, nn, nullcontext, os, pad, partial, prepare_deepspeed, prepare_fsdp, print_prompt_completions_sample, profiling_context, profiling_decorator, re, seed_worker, selective_log_softmax, set_seed, shuffle_tensor_dict, split_tensor_dict, textwrap, torch, transformers, unwrap_model_for_generation, version, wandb, warnings, Any, FSDP, Union, apply_chat_template, broadcast_object_list, gather, gather_object, is_conversational, maybe_apply_chat_template, nanstd, nullcontext, os, pad, profiling_context, re, torch, unwrap_model_for_generation, os, re, selective_log_softmax, torch, transformers, re, Any, Union, os, profiling_decorator, re, shuffle_tensor_dict, split_tensor_dict, torch, Optional, PreTrainedModel, Trainer, is_peft_available, os, re, torch, FSDP, nn, os, re, GRPOTrainer, Trainer, gather, os, re, torch)


import os
from typing import *
from dataclasses import dataclass, field
from packaging.version import Version
import torch
import numpy as np
from contextlib import nullcontext
from torch.nn import functional as F
from transformers import DataCollatorForSeq2Seq, DataCollatorForLanguageModeling as TransformersDataCollatorForLanguageModeling

torch_compile_options = {
    "epilogue_fusion"   : True,
    "max_autotune"      : False,
    "shape_padding"     : True,
    "trace.enabled"     : False,
    "triton.cudagraphs" : False,
}

@torch.compile(dynamic = True, fullgraph = True, options = torch_compile_options,)
def chunked_selective_log_softmax(logits, index):
    # Split into 4 chunks only
    chunked_logits = torch.chunk(logits.reshape(-1, logits.shape[-1]), chunks = 4, dim = 0)
    chunked_index  = torch.chunk(index.reshape(-1), chunks = 4, dim = 0)
    all_per_token_logps = []
    # Below loop does the same as selective_log_softmax(chunk_logits, chunk_index)
    for chunk_logits, chunk_index in zip(chunked_logits, chunked_index):
        chunk_logits = chunk_logits.to(torch.float32)
        selected_logits = torch.gather(chunk_logits, dim = -1, index = chunk_index.unsqueeze(-1)).squeeze(-1)
        logsumexp_values = torch.logsumexp(chunk_logits, dim = -1)
        per_token_logps = selected_logits - logsumexp_values
        all_per_token_logps.append(per_token_logps)
    pass
    all_per_token_logps = torch.concat(all_per_token_logps)
    all_per_token_logps = all_per_token_logps.reshape((logits.shape[0], logits.shape[1]))
    return all_per_token_logps

def grpo_compute_loss(
    ref_logits,
    new_logits,
    old_logits,
    input_ids,
    mask,
    beta,
    advantages,
    **kwargs
):
    # All Unsloth Zoo code licensed under LGPLv3
    # Set defaults for optional arguments
    loss_type = kwargs.get("loss_type", "grpo")
    epsilon_low = kwargs.get("epsilon_low", 0.2)
    epsilon_high = kwargs.get("epsilon_high", 0.2)
    max_completion_length = kwargs.get("max_completion_length", 8192)
    delta = kwargs.get("delta", None)
    temperature = kwargs.get("temperature", 1.0)
    logit_scale_multiply = kwargs.get("logit_scale_multiply", 0.0)
    logit_scale_divide   = kwargs.get("logit_scale_divide", 0.0)
    logit_softcapping    = kwargs.get("logit_softcapping", 0.0)

    input_ids = input_ids.unsqueeze(-1)

    # Optional logit softcapping and logit dividing
    if logit_scale_multiply != 0: new_logits = new_logits * logit_scale_multiply
    if logit_scale_divide   != 0: new_logits = new_logits / logit_scale_divide
    if logit_softcapping    != 0: new_logits = new_logits * torch.tanh(new_logits / logit_softcapping)

    new_logits = new_logits.to(torch.float32)
    # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
    if temperature != 1.0: new_logits = new_logits / temperature
    new_x = torch.gather(new_logits, dim = -1, index = input_ids).squeeze(-1)
    new = new_x - torch.logsumexp(new_logits, dim = -1)

    # x_i - logsumexp(x_i)
    with torch.no_grad():
        if beta != 0.0:
            assert ref_logits is not None, "ref_logits should not be None when beta != 0.0"
            
            # Optional logit softcapping and logit dividing
            if logit_scale_multiply != 0: ref_logits = ref_logits * logit_scale_multiply
            if logit_scale_divide   != 0: ref_logits = ref_logits / logit_scale_divide
            if logit_softcapping    != 0: ref_logits = ref_logits * torch.tanh(ref_logits / logit_softcapping)

            ref_logits = ref_logits.to(torch.float32)
            # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
            if temperature != 1.0: ref_logits = ref_logits / temperature
            ref_x = torch.gather(ref_logits, dim = -1, index = input_ids).squeeze(-1)
            ref = ref_x - torch.logsumexp(ref_logits, dim = -1)
        pass

        if old_logits is not None:
            # Optional logit softcapping and logit dividing
            if logit_scale_multiply != 0: old_logits = old_logits * logit_scale_multiply
            if logit_scale_divide   != 0: old_logits = old_logits / logit_scale_divide
            if logit_softcapping    != 0: old_logits = old_logits * torch.tanh(old_logits / logit_softcapping)

            old_logits = old_logits.to(torch.float32)
            # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
            if temperature != 1.0: old_logits = old_logits / temperature
            old_x = torch.gather(old_logits, dim = -1, index = input_ids).squeeze(-1)
            old = old_x - torch.logsumexp(old_logits, dim = -1)
        pass
    pass

    # Reverse KL
    # Note that this is a low variance low bias estimator for the KL divergence as used in GRPO paper
    if beta != 0.0:
        kl_i = torch.exp(ref - new) - (ref - new) - 1.0

    else:
        kl_i = 0.0 # set it to 0 to not effect the downstream computation
    # Full correct reverse KL divergence?? Missing term maybe?
    # kl_i = torch.exp(new) * kl_i

    # Below is forward KL (normal KL)
    # kl_i = torch.exp(old) * (old - new)
    if old_logits is not None: 
        coef_1 = torch.exp(new - old)
    else:
        coef_1 = torch.exp(new - new.detach())
    coef_2 = torch.clamp(coef_1, 1 - epsilon_low, 1 + epsilon_high)

    if delta is not None:
        loss_1 = torch.clamp(coef_1, max=delta) * advantages.unsqueeze(1)
    else:
        loss_1 = coef_1 * advantages.unsqueeze(1)
    pass

    # Must detach - otherwise gradients are not propagated correctly!
    # exp(x - x) == 1
    # loss_i = torch.exp(new - new.detach()) * advantages.unsqueeze(1)

    loss_2 = coef_2 * advantages.unsqueeze(1)
    loss_i = -torch.min(loss_1, loss_2)
    if beta != 0.0:
        loss_i = loss_i + beta * kl_i

    mask = mask.to(torch.float32)
    n_mask_per_reward = mask.sum(1)

    # https://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py#L1363-L1370
    if loss_type == "grpo":
        loss = ((loss_i * mask).sum(-1) / mask.sum(-1).clamp(min=1.0)).mean()
    elif loss_type == "bnpo":
        loss = (loss_i * mask).sum() / mask.sum().clamp(min=1.0)
    elif loss_type == "dr_grpo":
        loss = (loss_i * mask).sum() / (loss_i.size(0) * max_completion_length)
    else:
        raise ValueError(f"Unknown loss type: {loss_type}")

    # loss = (loss_i * mask).sum() / mask.sum()
    
    # Get metrics as well which are folded
    with torch.inference_mode():
        completion_length = n_mask_per_reward.mean()
        mean_kl_per_reward = (kl_i * mask).sum(1) / n_mask_per_reward
        mean_kl = mean_kl_per_reward.mean()
    pass

    return loss, completion_length, mean_kl

class UnslothEfficientGRPO(torch.autograd.Function):
    # All Unsloth Zoo code licensed under LGPLv3
    @staticmethod
    def forward(ctx, _new_hidden_states, _old_hidden_states, _ref_hidden_states, lm_head, _input_ids, _mask, _advantages, beta, scaler = None, n_chunks = 1, extra_kwargs=None):
        if extra_kwargs is None:
            extra_kwargs = {}
        def compute_loss(new_hidden_states, old_hidden_states, ref_hidden_states, input_ids, mask, advantages, scaling):
            new_logits = torch.matmul(new_hidden_states, lm_head.t())
            new_logits = new_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred
            with torch.no_grad():
                if beta != 0.0:
                    ref_logits = torch.matmul(ref_hidden_states, lm_head.t())
                    ref_logits = ref_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred 
                else:
                    ref_logits = None
                if old_hidden_states is not None:
                    old_logits = torch.matmul(old_hidden_states, lm_head.t())
                    old_logits = old_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred 
                else: 
                    old_logits = None
            # if old_hidden_states is not None: 
            #     old_logits = torch.matmul(old_hidden_states, lm_head.t()) #last logit already excluded
            #     old_logits = old_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred 
            # else:
            #     old_logits = None
            # unsloth_zoo/rl_replacements.py
            loss, completion_length, mean_kl = grpo_compute_loss(
                ref_logits,
                new_logits,
                old_logits,
                input_ids,
                mask,
                beta,
                advantages,
                **extra_kwargs,
            )

            # Scale loss if needed for mixed precision training
            scaled_loss = loss * scaling
            # Must add .loss.detach otherwise autograd uses 2x VRAM
            return scaled_loss, (loss.detach(), completion_length, mean_kl,)
        pass

        device =_new_hidden_states.device
        grad_inputs = torch.empty_like(_new_hidden_states)
        accumulated_loss              = torch.zeros(1, device = device)
        accumulated_completion_length = torch.zeros(1, device = device)
        accumulated_mean_kl           = torch.zeros(1, device = device)

        def accumulate_chunk(new_hidden_states_j, old_hidden_states_j, ref_hidden_states_j, input_ids_j, mask_j, advantages_j, scaling):
            (chunk_grad_input,), (chunk_loss, (unscaled_loss, chunk_completion_length, chunk_mean_kl,)) = torch.func.grad_and_value(
                compute_loss,
                argnums = (0,),
                has_aux = True,
            )(new_hidden_states_j, old_hidden_states_j, ref_hidden_states_j, input_ids_j, mask_j, advantages_j, scaling)
            accumulated_loss             .add_(unscaled_loss)
            accumulated_completion_length.add_(chunk_completion_length)
            accumulated_mean_kl          .add_(chunk_mean_kl)
            return chunk_grad_input
        pass

        accumulate_chunk = torch.compile(
            accumulate_chunk,
            fullgraph = True,
            options = torch_compile_options,
        )

        grad_inputs_chunks = torch.chunk(grad_inputs,        chunks = n_chunks, dim = 0)
        new_hidden_states  = torch.chunk(_new_hidden_states, chunks = n_chunks, dim = 0)
        if _old_hidden_states is not None: 
            old_hidden_states  = torch.chunk(_old_hidden_states, chunks = n_chunks, dim = 0)
        else: 
            old_hidden_states = [None] * n_chunks
        ref_hidden_states  = torch.chunk(_ref_hidden_states, chunks = n_chunks, dim = 0)
        input_ids          = torch.chunk(_input_ids,         chunks = n_chunks, dim = 0)
        mask               = torch.chunk(_mask,              chunks = n_chunks, dim = 0)
        advantages         = torch.chunk(_advantages,        chunks = n_chunks, dim = 0)

        # Get mixed precision scaling if seen
        scaling = scaler.get_scale() if scaler is not None else 1.0

        # Force torch.compile to use dynamic shapes for seqlen dim
        mark_dynamic = lambda x: torch._dynamo.mark_dynamic(x, 1)

        for (grad_inputs_j, new_hidden_states_j, old_hidden_states_j, ref_hidden_states_j,  input_ids_j, mask_j, advantages_j,) in \
            zip(grad_inputs_chunks, new_hidden_states, old_hidden_states, ref_hidden_states, input_ids, mask, advantages):

            mark_dynamic(new_hidden_states_j)
            mark_dynamic(ref_hidden_states_j)
            if old_hidden_states_j is not None: 
                mark_dynamic(old_hidden_states_j)
            mark_dynamic(input_ids_j)
            mark_dynamic(mask_j)

            
            grad_inputs_j.copy_(accumulate_chunk(new_hidden_states_j, old_hidden_states_j,ref_hidden_states_j,  input_ids_j, mask_j, advantages_j, scaling))
        pass

        grad_inputs                  .div_(n_chunks)
        accumulated_loss             .div_(n_chunks)
        accumulated_completion_length.div_(n_chunks)
        accumulated_mean_kl          .div_(n_chunks)
        ctx.save_for_backward(grad_inputs)
        return (
            accumulated_loss,
            accumulated_completion_length,
            accumulated_mean_kl,
        )
    pass

    @staticmethod
    def backward(ctx, grad_output, dcompletion_length, dmean_kl):
        (grad_input,) = ctx.saved_tensors
        return (grad_input, None, None, None, None, None, None, None, None, None, None)
    pass

def grpo_accumulated_loss(
    trainer,
    input_ids,
    attention_mask,
    logits_to_keep,
    completion_mask,
    advantages,
    old_hidden_states,
    n_chunks = -1,
    **kwargs,
):
    # All Unsloth Zoo code licensed under LGPLv3
    bsz, qlen = input_ids.shape

    # Find closest multiple
    factors = [i for i in range(1, bsz + 1) if bsz % i == 0]
    if n_chunks == -1: n_chunks = bsz
    n_chunks = factors[min(np.searchsorted(factors, n_chunks), len(factors)-1)]

    if not hasattr(trainer, '_autocast_dtype'):
        trainer._autocast_dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16
        if os.environ.get('UNSLOTH_FORCE_FLOAT32', '0') == '1': trainer._autocast_dtype = torch.float16
    pass
    os.environ["UNSLOTH_RETURN_HIDDEN_STATES"] = "1"

    completion_input_ids = input_ids[:, -logits_to_keep:]
    lm_head = trainer.model.get_output_embeddings().weight

    with torch.amp.autocast(device_type = trainer.model.device.type, dtype = trainer._autocast_dtype):
        with torch.inference_mode(), trainer.accelerator.unwrap_model(trainer.model, keep_fp32_wrapper = False).disable_adapter():
            ref_hidden_states = trainer.model(
                input_ids = input_ids,
                attention_mask = attention_mask,
                logits_to_keep = logits_to_keep + 1,
            ).logits
        pass
        new_hidden_states = trainer.model(
            input_ids = input_ids,
            attention_mask = attention_mask,
            logits_to_keep = logits_to_keep + 1,
        ).logits

        loss, completion_length, mean_kl = UnslothEfficientGRPO.apply(
            new_hidden_states,
            old_hidden_states,
            ref_hidden_states,
            lm_head,
            completion_input_ids,
            completion_mask,
            advantages,
            trainer.beta,
            trainer.accelerator.scaler,
            n_chunks,
            kwargs # pass kwargs as a dict
        )
    pass
    # Must force not returning hidden states but logits otherwise gibberish
    os.environ["UNSLOTH_RETURN_HIDDEN_STATES"] = "0"
    return loss, completion_length, mean_kl

    # Old non efficient code path
    new_logits = torch.matmul(new_hidden_states, lm_head.t())
    new_logits = new_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred
    old_logits = torch.matmul(old_hidden_states, lm_head.t())
    old_logits = old_logits[:, :-1, :] # exclude the last logit: it corresponds to the next token pred
    loss, completion_length, mean_kl = grpo_compute_loss(
        old_logits,
        new_logits,
        completion_input_ids,
        completion_mask,
        trainer.beta,
        advantages,
    )
    return loss, completion_length, mean_kl
    pass

@torch.compile(dynamic = True, fullgraph = True, options = torch_compile_options)
def grpo_compute_loss_slow(
    ref_logits,
    new_logits,
    old_logits,
    input_ids,
    mask,
    beta,
    advantages,
    **kwargs
):
    # All Unsloth Zoo code licensed under LGPLv3
    # Set defaults for optional arguments
    loss_type = kwargs.get("loss_type", "grpo")
    epsilon_low = kwargs.get("epsilon_low", 0.2)
    epsilon_high = kwargs.get("epsilon_high", 0.2)
    max_completion_length = kwargs.get("max_completion_length", 8192)
    delta = kwargs.get("delta", None)
    temperature = kwargs.get("temperature", 1.0)
    logit_scale_multiply = kwargs.get("logit_scale_multiply", 0.0)
    logit_scale_divide   = kwargs.get("logit_scale_divide", 0.0)
    logit_softcapping    = kwargs.get("logit_softcapping", 0.0)

    input_ids = input_ids.unsqueeze(-1)

    # Optional logit softcapping and logit dividing
    if logit_scale_multiply != 0: new_logits = new_logits * logit_scale_multiply
    if logit_scale_divide   != 0: new_logits = new_logits / logit_scale_divide
    if logit_softcapping    != 0: new_logits = new_logits * torch.tanh(new_logits / logit_softcapping)

    new_logits = new_logits.to(torch.float32)
    # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
    if temperature != 1.0: new_logits = new_logits / temperature
    new_x = torch.gather(new_logits, dim = -1, index = input_ids).squeeze(-1)
    new = new_x - torch.logsumexp(new_logits, dim = -1)

    # x_i - logsumexp(x_i)
    with torch.no_grad():
        if beta != 0.0:
            assert ref_logits is not None, "ref_logits should not be None when beta != 0.0"
            
            # Optional logit softcapping and logit dividing
            if logit_scale_multiply != 0: ref_logits = ref_logits * logit_scale_multiply
            if logit_scale_divide   != 0: ref_logits = ref_logits / logit_scale_divide
            if logit_softcapping    != 0: ref_logits = ref_logits * torch.tanh(ref_logits / logit_softcapping)

            ref_logits = ref_logits.to(torch.float32)
            # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
            if temperature != 1.0: ref_logits = ref_logits / temperature
            ref_x = torch.gather(ref_logits, dim = -1, index = input_ids).squeeze(-1)
            ref = ref_x - torch.logsumexp(ref_logits, dim = -1)
        pass

        if old_logits is not None:
            # Optional logit softcapping and logit dividing
            if logit_scale_multiply != 0: old_logits = old_logits * logit_scale_multiply
            if logit_scale_divide   != 0: old_logits = old_logits / logit_scale_divide
            if logit_softcapping    != 0: old_logits = old_logits * torch.tanh(old_logits / logit_softcapping)

            old_logits = old_logits.to(torch.float32)
            # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
            if temperature != 1.0: old_logits = old_logits / temperature
            old_x = torch.gather(old_logits, dim = -1, index = input_ids).squeeze(-1)
            old = old_x - torch.logsumexp(old_logits, dim = -1)
        pass
    pass

    # Reverse KL
    # Note that this is a low variance low bias estimator for the KL divergence as used in GRPO paper
    if beta != 0.0:
        kl_i = torch.exp(ref - new) - (ref - new) - 1.0

    else:
        kl_i = 0.0 # set it to 0 to not effect the downstream computation
    # Full correct reverse KL divergence?? Missing term maybe?
    # kl_i = torch.exp(new) * kl_i

    # Below is forward KL (normal KL)
    # kl_i = torch.exp(old) * (old - new)
    if old_logits is not None: 
        coef_1 = torch.exp(new - old)
    else:
        coef_1 = torch.exp(new - new.detach())
    coef_2 = torch.clamp(coef_1, 1 - epsilon_low, 1 + epsilon_high)

    if delta is not None:
        loss_1 = torch.clamp(coef_1, max=delta) * advantages.unsqueeze(1)
    else:
        loss_1 = coef_1 * advantages.unsqueeze(1)
    pass

    # Must detach - otherwise gradients are not propagated correctly!
    # exp(x - x) == 1
    # loss_i = torch.exp(new - new.detach()) * advantages.unsqueeze(1)

    loss_2 = coef_2 * advantages.unsqueeze(1)
    loss_i = -torch.min(loss_1, loss_2)
    if beta != 0.0:
        loss_i = loss_i + beta * kl_i

    mask = mask.to(torch.float32)
    n_mask_per_reward = mask.sum(1)

    # https://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py#L1363-L1370
    if loss_type == "grpo":
        loss = ((loss_i * mask).sum(-1) / mask.sum(-1).clamp(min=1.0)).mean()
    elif loss_type == "bnpo":
        loss = (loss_i * mask).sum() / mask.sum().clamp(min=1.0)
    elif loss_type == "dr_grpo":
        loss = (loss_i * mask).sum() / (loss_i.size(0) * max_completion_length)
    else:
        raise ValueError(f"Unknown loss type: {loss_type}")

    # loss = (loss_i * mask).sum() / mask.sum()
    
    # Get metrics as well which are folded
    with torch.inference_mode():
        completion_length = n_mask_per_reward.mean()
        mean_kl_per_reward = (kl_i * mask).sum(1) / n_mask_per_reward
        mean_kl = mean_kl_per_reward.mean()
    pass

    return loss, completion_length, mean_kl

def vLLMSamplingParams(**kwargs):
    from vllm import SamplingParams
    sampling_params = SamplingParams(**kwargs)
    sampling_params._set_kwargs = kwargs
    return sampling_params
@dataclass
class UnslothGRPOConfig(GRPOConfig):
    """
    
    Configuration class for the [`GRPOTrainer`].

    This class includes only the parameters that are specific to GRPO training. For a full list of training arguments,
    please refer to the [`~transformers.TrainingArguments`] documentation. Note that default values in this class may
    differ from those in [`~transformers.TrainingArguments`].

    Using [`~transformers.HfArgumentParser`] we can turn this class into
    [argparse](https://docs.python.org/3/library/argparse#module-argparse) arguments that can be specified on the
    command line.

    Parameters:
        > Parameters that control the model and reference model

        model_init_kwargs (`str`, `dict[str, Any]` or `None`, *optional*, defaults to `None`):
            Keyword arguments for [`~transformers.AutoModelForCausalLM.from_pretrained`], used when the `model`
            argument of the [`GRPOTrainer`] is provided as a string.
        disable_dropout (`bool`, *optional*, defaults to `False`):
            Whether to disable dropout in the model. This is useful for training with a reference model, as it prevents
            the model from generating different logprobs for the same input.

        > Parameters that control the data preprocessing

        remove_unused_columns (`bool`, *optional*, defaults to `False`):
            Whether to only keep the column `"prompt"` in the dataset. If you use a custom reward function that
            requires any column other than `"prompts"` and `"completions"`, you should keep this to `False`.
        max_prompt_length (`int` or `None`, *optional*, defaults to `512`):
            Maximum length of the prompt. If the prompt is longer than this value, it will be truncated left.
        num_generations (`int` or `None`, *optional*, defaults to `8`):
            Number of generations per prompt to sample. The effective batch size (num_processes * per_device_batch_size
            * gradient_accumulation_steps) must be evenly divisible by this value.
        max_completion_length (`int` or `None`, *optional*, defaults to `256`):
            Maximum length of the generated completion.
        ds3_gather_for_generation (`bool`, *optional*, defaults to `True`):
            This setting applies to DeepSpeed ZeRO-3. If enabled, the policy model weights are gathered for generation,
            improving generation speed. However, disabling this option allows training models that exceed the VRAM
            capacity of a single GPU, albeit at the cost of slower generation. Disabling this option is not compatible
            with vLLM generation.
        shuffle_dataset (`bool`, *optional*, defaults to `True`):
            Whether to shuffle the training dataset.

        > Parameters that control generation

        generation_batch_size: (`int` or `None`, *optional*, defaults to `None`):
            Batch size to use for generation. If `None`, it defaults to the effective training batch size:
            `per_device_train_batch_size * num_processes * gradient_accumulation_steps`.
        steps_per_generations: (`int` or `None`, *optional*, defaults to `None`):
            Number of optimization steps per generation. If `None`, it defaults to gradient_accumulation_steps.
        temperature (`float`, defaults to `1.0`):
            Temperature for sampling. The higher the temperature, the more random the completions.
        top_p (`float`, *optional*, defaults to `1.0`):
            Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to
            `1.0` to consider all tokens.
        top_k (`int` or `None`, *optional*, defaults to `None`):
            Number of highest probability vocabulary tokens to keep for top-k-filtering. If `None`, top-k-filtering is
            disabled and all tokens are considered.
        min_p (`float` or `None`, *optional*, defaults to `None`):
            Minimum token probability, which will be scaled by the probability of the most likely token. It must be a
            value between `0.0` and `1.0`. Typical values are in the `0.01-0.2` range.
        repetition_penalty (`float`, *optional*, defaults to `1.0`):
            Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far.
            Values > `1.0` encourage the model to use new tokens, while values < `1.0` encourage the model to repeat
            tokens.
        cache_implementation (`str` or `None`, *optional*, defaults to `None`):
            Implementation of the cache method for faster generation when use_vllm is set to False.
        generation_kwargs (`dict[str, Any]` or `None`, *optional*, defaults to `None`):
            Additional keyword arguments to pass to `GenerationConfig` (if using transformers) or `SamplingParams` (if
            using vLLM) when sampling completions. This can be used to further customize the generation behavior, such
            as setting `supress_tokens`, `num_beams`, etc. If it contains keys that conflict with the other generation
            parameters (like `min_p`, `top_p`, etc.), they will override them.

        > Parameters that control generation acceleration powered by vLLM

        use_vllm (`bool`, *optional*, defaults to `False`):
            Whether to use vLLM for generating completions. If set to `True`, the trainer will use vLLM for generation
            instead of the default model.generate(). Requires `vllm` to be installed.
        vllm_mode (`str`, *optional*, defaults to `"server"`):
            Mode to use for vLLM integration when `use_vllm` is set to `True`. Must be one of `"server"` or
            `"colocate"`.

            - `"server"`: The trainer will send generation requests to a separate vLLM server. Make sure a TRL vLLM
              server is running (start with `trl vllm-serve`).
            - `"colocate"`: vLLM will run in the same process and share the training GPUs. This avoids the need for a
              separate server but may cause resource contention with training.
        vllm_guided_decoding_regex (`str` or `None`, *optional*, defaults to `None`):
            Regex for vLLM guided decoding. If `None` (default), guided decoding is disabled.

        > Parameters that control the vLLM server (only used when `vllm_mode` is `"server"`)
        vllm_server_base_url (`str` or `None`, *optional*, defaults to `None`):
            Base URL for the vLLM server (e.g., `"http://localhost:8000"`). If provided, `vllm_server_host` and
            `vllm_server_port` are ignored.
        vllm_server_host (`str`, *optional*, defaults to `"0.0.0.0"`):
            Host of the vLLM server to connect to. Ignored if `vllm_server_base_url` is provided.
        vllm_server_port (`int`, *optional*, defaults to `8000`):
            Port of the vLLM server to connect to. Ignored if `vllm_server_base_url` is provided.
        vllm_server_timeout (`float`, *optional*, defaults to `240.0`):
            Total timeout duration in seconds to wait for the vLLM server to be up. If the server is not up after the
            timeout, a `ConnectionError` is raised.

        > Parameters that control colocated vLLM execution (only used when `vllm_mode` is `"colocate"`)

        vllm_gpu_memory_utilization (`float`, *optional*, defaults to `0.3`):
            Control the GPU memory utilization for vLLM. This setting only applies when `vllm_mode` is set to
            `"colocate"`. If you are using `vllm_mode="server"`, this parameter must be passed separately when
            launching the vLLM server via the `--vllm_gpu_memory_utilization` flag.
        vllm_tensor_parallel_size (`int`, *optional*, defaults to `1`):
            Control the tensor parallel size for vLLM. This setting only applies when `vllm_mode` is set to
            `"colocate"`. If you are using `vllm_mode="server"`, this parameter must be passed separately when
            launching the vLLM server via the `--vllm_tensor_parallel_size` flag.

        > Parameters that control the training

        beta (`float`, *optional*, defaults to `0.0`):
            KL coefficient. If `0.0` (default), the reference model is not loaded, reducing memory usage and improving
            training speed.
        num_iterations (`int`, *optional*, defaults to `1`):
            Number of iterations per batch (denoted as μ in the algorithm).
        epsilon (`float`, *optional*, defaults to `0.2`):
            Epsilon value for clipping.
        delta: (`float` or `None`, *optional*, defaults to `None`):
            Enables the upper clipping bound in two-sided GRPO loss when set to a float. If `None` (default), standard
            GRPO clipping is used. Recommended to be greater than `1 + ε` when enabled. This method is introduced in
            the [INTELLECT-2 tech report](https://huggingface.co/papers/2505.07291).
        epsilon_high (`float` or `None`, *optional*, defaults to `None`):
            Upper-bound epsilon value for clipping. If not specified, it defaults to the same value as the lower-bound
            specified in argument `epsilon`. Paper [DAPO](https://huggingface.co/papers/2503.14476) recommends `0.28`.
        reward_weights (`list[float]` or `None`, *optional*, defaults to `None`):
            Weights for each reward function. Must match the number of reward functions. If `None`, all rewards are
            weighted equally with weight `1.0`.
        scale_rewards (`bool`, *optional*, defaults to `True`):
            Whether to scale the rewards by dividing them by their standard deviation. If `True` (default), the rewards
            are normalized by the standard deviation, ensuring they have unit variance. If `False`, no scaling is
            applied. The [Dr. GRPO paper](https://huggingface.co/papers/2503.20783) recommends not scaling the rewards,
            as scaling by the standard deviation introduces a question-level difficulty bias.
        loss_type (`str`, *optional*, defaults to `"bnpo"`):
            Specifies the loss formulation to use. Supported values are:

            - `"grpo"`: Aggregates token-level losses by normalizing over sequence length. Not recommended due to
                length bias—this approach tends to prefer shorter completions with positive advantages and longer ones
                with negative advantages.
            - `"bnpo"`: Aggregates token-level losses by normalizing number of active token in the local batch.
                Note that normalization is performed over the local batch only, so results may slightly vary depending
                on the local batch size, despite a constant effective batch size. When using
                `per_device_train_batch_size==1`, the loss is equivalent to the GRPO loss.
            - `"dr_grpo"`: Aggregates token-level losses by normalizing with a global constant. This method was
                introduced in the [Dr. GRPO paper](https://huggingface.co/papers/2503.20783) to eliminate length bias.
                The value of the constant corresponds to `max_completion_length`.
        mask_truncated_completions (`bool`, *optional*, defaults to `False`):
            When enabled, truncated completions are excluded from the loss calculation, preventing them from being
            incorrectly penalized and introducing noise during training. According to the
            [DAPO](https://huggingface.co/papers/2503.14476) paper, this is a good practice for training stability.
        sync_ref_model (`bool`, *optional*, defaults to `False`):
            Whether to synchronize the reference model with the active model every `ref_model_sync_steps` steps, using
            the `ref_model_mixup_alpha` parameter. This synchronization originates from the
            [TR-DPO](https://huggingface.co/papers/2404.09656) paper.
        ref_model_mixup_alpha (`float`, *optional*, defaults to `0.6`):
            α parameter from the [TR-DPO](https://huggingface.co/papers/2404.09656) paper, which controls the mix
            between the current policy and the previous reference policy during updates. The reference policy is
            updated according to the equation: `π_ref = α * π_θ + (1 - α) * π_ref_prev`. To use this parameter, you
            must set `sync_ref_model=True`.
        ref_model_sync_steps (`int`, *optional*, defaults to `512`):
            τ parameter from the [TR-DPO](https://huggingface.co/papers/2404.09656) paper, which determines how
            frequently the current policy is synchronized with the reference policy. To use this parameter, you must
            set `sync_ref_model=True`.
        use_liger_loss (`bool`, *optional*, defaults to `False`):
            Whether to use the Liger GRPO loss.

        > Parameters that control the logging

        log_completions (`bool`, *optional*, defaults to `False`):
            Whether to log a sample of (prompt, completion) pairs every `logging_steps` steps. If `rich` is installed,
            it prints the sample. If `wandb` logging is enabled, it logs it to `wandb`.
        num_completions_to_print (`int` or `None`, *optional*, defaults to `None`):
            Number of completions to print with `rich`. If `None`, all completions are logged.
        wandb_log_unique_prompts (`bool`, *optional*, defaults to `False`):
            Whether to log unique prompts in wandb. If `True`, only unique prompts are logged. If `False`, all prompts
            are logged.
    
    """
    vllm_sampling_params: Optional[Any] = field(
        default = None,
        metadata = {'help': 'vLLM SamplingParams'},
    )
    unsloth_num_chunks : Optional[int] = field(
        default = -1,
        metadata = {'help': 'Chunk size to reduce memory usage. -1 is most efficient.'},
    )
    def __init__(
        self,
        output_dir = None,
        overwrite_output_dir = None,
        do_train = False,
        do_eval = False,
        do_predict = False,
        eval_strategy = 'no',
        prediction_loss_only = False,
        per_device_train_batch_size = 4,
        per_device_eval_batch_size = 4,
        per_gpu_train_batch_size = None,
        per_gpu_eval_batch_size = None,
        gradient_accumulation_steps = 2,
        eval_accumulation_steps = 2,
        eval_delay = 0,
        torch_empty_cache_steps = 250,
        learning_rate = 5e-05,
        weight_decay = 0.01,
        adam_beta1 = 0.9,
        adam_beta2 = 0.999,
        adam_epsilon = 1e-08,
        max_grad_norm = 1.0,
        num_train_epochs = 3.0,
        max_steps = -1,
        lr_scheduler_type = 'linear',
        warmup_ratio = 0.1,
        warmup_steps = 0,
        log_level = 'passive',
        log_level_replica = 'warning',
        log_on_each_node = True,
        logging_dir = None,
        logging_strategy = 'steps',
        logging_first_step = False,
        logging_steps = 1,
        logging_nan_inf_filter = False,
        save_strategy = 'steps',
        save_steps = 500,
        save_total_limit = None,
        save_safetensors = True,
        save_on_each_node = False,
        save_only_model = False,
        restore_callback_states_from_checkpoint = False,
        no_cuda = False,
        use_cpu = False,
        use_mps_device = False,
        seed = 3407,
        data_seed = 3407,
        jit_mode_eval = False,
        use_ipex = False,
        bf16 = False,
        fp16 = False,
        fp16_opt_level = 'O1',
        half_precision_backend = 'auto',
        bf16_full_eval = False,
        fp16_full_eval = False,
        tf32 = None,
        local_rank = -1,
        ddp_backend = None,
        tpu_num_cores = None,
        tpu_metrics_debug = False,
        debug = '',
        dataloader_drop_last = False,
        eval_steps = None,
        dataloader_num_workers = 0,
        dataloader_prefetch_factor = None,
        past_index = -1,
        run_name = None,
        disable_tqdm = None,
        remove_unused_columns = False,
        label_names = None,
        load_best_model_at_end = False,
        metric_for_best_model = None,
        greater_is_better = None,
        ignore_data_skip = False,
        fsdp = '',
        fsdp_min_num_params = 0,
        fsdp_config = None,
        fsdp_transformer_layer_cls_to_wrap = None,
        accelerator_config = None,
        deepspeed = None,
        label_smoothing_factor = 0.0,
        optim = 'adamw_8bit',
        optim_args = None,
        adafactor = False,
        group_by_length = False,
        length_column_name = 'length',
        report_to = None,
        ddp_find_unused_parameters = None,
        ddp_bucket_cap_mb = None,
        ddp_broadcast_buffers = None,
        dataloader_pin_memory = True,
        dataloader_persistent_workers = False,
        skip_memory_metrics = True,
        use_legacy_prediction_loop = False,
        push_to_hub = False,
        resume_from_checkpoint = None,
        hub_model_id = None,
        hub_strategy = 'every_save',
        hub_token = None,
        hub_private_repo = None,
        hub_always_push = False,
        hub_revision = None,
        gradient_checkpointing = False,
        gradient_checkpointing_kwargs = None,
        include_inputs_for_metrics = False,
        eval_do_concat_batches = True,
        fp16_backend = 'auto',
        push_to_hub_model_id = None,
        push_to_hub_organization = None,
        push_to_hub_token = None,
        mp_parameters = '',
        auto_find_batch_size = True,
        full_determinism = False,
        torchdynamo = None,
        ray_scope = 'last',
        ddp_timeout = 1800,
        torch_compile = False,
        torch_compile_backend = None,
        torch_compile_mode = None,
        include_tokens_per_second = False,
        include_num_input_tokens_seen = False,
        neftune_noise_alpha = None,
        optim_target_modules = None,
        batch_eval_metrics = False,
        eval_on_start = False,
        use_liger_kernel = False,
        liger_kernel_config = None,
        eval_use_gather_object = False,
        average_tokens_across_devices = False,
        model_init_kwargs = None,
        disable_dropout = False,
        max_prompt_length = 512,
        num_generations = 8,
        max_completion_length = 256,
        ds3_gather_for_generation = True,
        shuffle_dataset = True,
        generation_batch_size = None,
        steps_per_generation = None,
        temperature = 1.0,
        top_p = 1.0,
        top_k = None,
        min_p = None,
        generation_kwargs = {},
        repetition_penalty = 1.0,
        cache_implementation = None,
        use_vllm = False,
        vllm_server_base_url = None,
        vllm_mode = 'colocate',
        vllm_guided_decoding_regex = None,
        vllm_server_host = '0.0.0.0',
        vllm_server_port = 8000,
        vllm_server_timeout = 240.0,
        vllm_gpu_memory_utilization = 0.3,
        vllm_tensor_parallel_size = 1,
        beta = 0.001,
        num_iterations = 1,
        epsilon = 0.2,
        delta = None,
        epsilon_high = None,
        reward_weights = None,
        scale_rewards = True,
        loss_type = 'bnpo',
        mask_truncated_completions = False,
        sync_ref_model = False,
        ref_model_mixup_alpha = 0.6,
        ref_model_sync_steps = 512,
        use_liger_loss = False,
        log_completions = False,
        num_completions_to_print = None,
        wandb_log_unique_prompts = False,
        vllm_sampling_params = None,
        unsloth_num_chunks = -1,
        **kwargs,
    ):
        if learning_rate < 1e-7: raise FloatingPointError(f'Unsloth: Your learning rate of `{learning_rate}` is too small and less than 1e-7! Consider increasing it, otherwise gradient updates will be close to 0!')
        if learning_rate > 1: raise OverflowError(f'Unsloth: Your learning rate of `{learning_rate}` is way too larger > 1! Consider decreasing it to 1e-1, otherwise gradient updates will explode!')
        if output_dir is None and save_strategy == 'steps' and save_steps == 500:
            output_dir = 'unsloth_training_checkpoints'
            save_strategy = 'no'
        if loss_type.lower() == 'dr_grpo':
            loss_type = 'dr_grpo'
        elif loss_type.lower() == 'dapo':
            loss_type = 'dapo'
        if loss_type.lower() == 'dr_grpo':
            if scale_rewards == None:
                scale_rewards = True
            elif scale_rewards == True:
                print('Unsloth: The Dr GRPO paper recommends setting `scale_rewards` to False! Will override. Set it to `None` to force False.')
                scale_rewards = False
        elif loss_type.lower() == 'dapo':
            print('Unsloth: The DAPO paper recommends `mask_truncated_completions = True`')
            print('Unsloth: The DAPO paper recommends `epsilon_high = 0.28`')
            print('Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term')
            mask_truncated_completions = True
            epsilon_high = 0.28
            beta = 0.0
            loss_type = 'bnpo'
        
        if (per_device_train_batch_size // num_generations) * num_generations != per_device_train_batch_size:
            print('Unsloth: We now expect `per_device_train_batch_size` to be a multiple of `num_generations`.\nWe will change the batch size of ' + str(per_device_train_batch_size) + ' to the `num_generations` of ' + str(num_generations))
            per_device_train_batch_size = num_generations
        
        if temperature <= 0:
            raise MathError('Unsloth: Please set a positive non-zero temperature since your results will be wrong.')
        elif temperature >= 10:
            raise MathError('Unsloth: Please set a positive non-zero temperature less than 10, since sampling will be quite erratic.')
        
        
        super().__init__(
            output_dir = output_dir,
            overwrite_output_dir = overwrite_output_dir,
            do_train = do_train,
            do_eval = do_eval,
            do_predict = do_predict,
            eval_strategy = eval_strategy,
            prediction_loss_only = prediction_loss_only,
            per_device_train_batch_size = per_device_train_batch_size,
            per_device_eval_batch_size = per_device_eval_batch_size,
            per_gpu_train_batch_size = per_gpu_train_batch_size,
            per_gpu_eval_batch_size = per_gpu_eval_batch_size,
            gradient_accumulation_steps = gradient_accumulation_steps,
            eval_accumulation_steps = eval_accumulation_steps,
            eval_delay = eval_delay,
            torch_empty_cache_steps = torch_empty_cache_steps,
            learning_rate = learning_rate,
            weight_decay = weight_decay,
            adam_beta1 = adam_beta1,
            adam_beta2 = adam_beta2,
            adam_epsilon = adam_epsilon,
            max_grad_norm = max_grad_norm,
            num_train_epochs = num_train_epochs,
            max_steps = max_steps,
            lr_scheduler_type = lr_scheduler_type,
            warmup_ratio = warmup_ratio,
            warmup_steps = warmup_steps,
            log_level = log_level,
            log_level_replica = log_level_replica,
            log_on_each_node = log_on_each_node,
            logging_dir = logging_dir,
            logging_strategy = logging_strategy,
            logging_first_step = logging_first_step,
            logging_steps = logging_steps,
            logging_nan_inf_filter = logging_nan_inf_filter,
            save_strategy = save_strategy,
            save_steps = save_steps,
            save_total_limit = save_total_limit,
            save_safetensors = save_safetensors,
            save_on_each_node = save_on_each_node,
            save_only_model = save_only_model,
            restore_callback_states_from_checkpoint = restore_callback_states_from_checkpoint,
            no_cuda = no_cuda,
            use_cpu = use_cpu,
            use_mps_device = use_mps_device,
            seed = seed,
            data_seed = data_seed,
            jit_mode_eval = jit_mode_eval,
            use_ipex = use_ipex,
            bf16 = bf16,
            fp16 = fp16,
            fp16_opt_level = fp16_opt_level,
            half_precision_backend = half_precision_backend,
            bf16_full_eval = bf16_full_eval,
            fp16_full_eval = fp16_full_eval,
            tf32 = tf32,
            local_rank = local_rank,
            ddp_backend = ddp_backend,
            tpu_num_cores = tpu_num_cores,
            tpu_metrics_debug = tpu_metrics_debug,
            debug = debug,
            dataloader_drop_last = dataloader_drop_last,
            eval_steps = eval_steps,
            dataloader_num_workers = dataloader_num_workers,
            dataloader_prefetch_factor = dataloader_prefetch_factor,
            past_index = past_index,
            run_name = run_name,
            disable_tqdm = disable_tqdm,
            remove_unused_columns = remove_unused_columns,
            label_names = label_names,
            load_best_model_at_end = load_best_model_at_end,
            metric_for_best_model = metric_for_best_model,
            greater_is_better = greater_is_better,
            ignore_data_skip = ignore_data_skip,
            fsdp = fsdp,
            fsdp_min_num_params = fsdp_min_num_params,
            fsdp_config = fsdp_config,
            fsdp_transformer_layer_cls_to_wrap = fsdp_transformer_layer_cls_to_wrap,
            accelerator_config = accelerator_config,
            deepspeed = deepspeed,
            label_smoothing_factor = label_smoothing_factor,
            optim = optim,
            optim_args = optim_args,
            adafactor = adafactor,
            group_by_length = group_by_length,
            length_column_name = length_column_name,
            report_to = report_to,
            ddp_find_unused_parameters = ddp_find_unused_parameters,
            ddp_bucket_cap_mb = ddp_bucket_cap_mb,
            ddp_broadcast_buffers = ddp_broadcast_buffers,
            dataloader_pin_memory = dataloader_pin_memory,
            dataloader_persistent_workers = dataloader_persistent_workers,
            skip_memory_metrics = skip_memory_metrics,
            use_legacy_prediction_loop = use_legacy_prediction_loop,
            push_to_hub = push_to_hub,
            resume_from_checkpoint = resume_from_checkpoint,
            hub_model_id = hub_model_id,
            hub_strategy = hub_strategy,
            hub_token = hub_token,
            hub_private_repo = hub_private_repo,
            hub_always_push = hub_always_push,
            hub_revision = hub_revision,
            gradient_checkpointing = gradient_checkpointing,
            gradient_checkpointing_kwargs = gradient_checkpointing_kwargs,
            include_inputs_for_metrics = include_inputs_for_metrics,
            eval_do_concat_batches = eval_do_concat_batches,
            fp16_backend = fp16_backend,
            push_to_hub_model_id = push_to_hub_model_id,
            push_to_hub_organization = push_to_hub_organization,
            push_to_hub_token = push_to_hub_token,
            mp_parameters = mp_parameters,
            auto_find_batch_size = auto_find_batch_size,
            full_determinism = full_determinism,
            torchdynamo = torchdynamo,
            ray_scope = ray_scope,
            ddp_timeout = ddp_timeout,
            torch_compile = torch_compile,
            torch_compile_backend = torch_compile_backend,
            torch_compile_mode = torch_compile_mode,
            include_tokens_per_second = include_tokens_per_second,
            include_num_input_tokens_seen = include_num_input_tokens_seen,
            neftune_noise_alpha = neftune_noise_alpha,
            optim_target_modules = optim_target_modules,
            batch_eval_metrics = batch_eval_metrics,
            eval_on_start = eval_on_start,
            use_liger_kernel = use_liger_kernel,
            liger_kernel_config = liger_kernel_config,
            eval_use_gather_object = eval_use_gather_object,
            average_tokens_across_devices = average_tokens_across_devices,
            model_init_kwargs = model_init_kwargs,
            disable_dropout = disable_dropout,
            max_prompt_length = max_prompt_length,
            num_generations = num_generations,
            max_completion_length = max_completion_length,
            ds3_gather_for_generation = ds3_gather_for_generation,
            shuffle_dataset = shuffle_dataset,
            generation_batch_size = generation_batch_size,
            steps_per_generation = steps_per_generation,
            temperature = temperature,
            top_p = top_p,
            top_k = top_k,
            min_p = min_p,
            generation_kwargs = generation_kwargs,
            repetition_penalty = repetition_penalty,
            cache_implementation = cache_implementation,
            use_vllm = use_vllm,
            vllm_server_base_url = vllm_server_base_url,
            vllm_mode = vllm_mode,
            vllm_guided_decoding_regex = vllm_guided_decoding_regex,
            vllm_server_host = vllm_server_host,
            vllm_server_port = vllm_server_port,
            vllm_server_timeout = vllm_server_timeout,
            vllm_gpu_memory_utilization = vllm_gpu_memory_utilization,
            vllm_tensor_parallel_size = vllm_tensor_parallel_size,
            beta = beta,
            num_iterations = num_iterations,
            epsilon = epsilon,
            delta = delta,
            epsilon_high = epsilon_high,
            reward_weights = reward_weights,
            scale_rewards = scale_rewards,
            loss_type = loss_type,
            mask_truncated_completions = mask_truncated_completions,
            sync_ref_model = sync_ref_model,
            ref_model_mixup_alpha = ref_model_mixup_alpha,
            ref_model_sync_steps = ref_model_sync_steps,
            use_liger_loss = use_liger_loss,
            log_completions = log_completions,
            num_completions_to_print = num_completions_to_print,
            wandb_log_unique_prompts = wandb_log_unique_prompts,**kwargs)
        self.vllm_sampling_params = vllm_sampling_params
        self.unsloth_num_chunks = unsloth_num_chunks
pass

class _UnslothGRPOTrainer(Trainer):
    """"""

    _tag_names = ["trl", "grpo"]

    def __init__(
        self,
        model: Union[str, PreTrainedModel],
        reward_funcs: Union[RewardFunc, list[RewardFunc]],
        args: Optional[GRPOConfig] = None,
        train_dataset: Optional[Union[Dataset, IterableDataset]] = None,
        eval_dataset: Optional[Union[Dataset, IterableDataset, dict[str, Union[Dataset, IterableDataset]]]] = None,
        processing_class: Optional[PreTrainedTokenizerBase] = None,
        reward_processing_classes: Optional[Union[PreTrainedTokenizerBase, list[PreTrainedTokenizerBase]]] = None,
        callbacks: Optional[list[TrainerCallback]] = None,
        optimizers: tuple[Optional[torch.optim.Optimizer], Optional[torch.optim.lr_scheduler.LambdaLR]] = (None, None),
        peft_config: Optional["PeftConfig"] = None,
    ):

        if hasattr(model, 'vllm_engine') and hasattr(args, 'use_vllm'):
            if (getattr(args, 'use_vllm', False) == False):
                args.use_vllm = True
            args.vllm_mode='colocate'
        # Args
        if args is None:
            model_name = model if isinstance(model, str) else model.config._name_or_path
            model_name = model_name.split("/")[-1]
            args = GRPOConfig(f"{model_name}-GRPO")

        # Models
        # Trained model
        model_init_kwargs = args.model_init_kwargs or {}
        if isinstance(model, str):
            model_id = model
            torch_dtype = model_init_kwargs.get("torch_dtype")
            if isinstance(torch_dtype, torch.dtype) or torch_dtype == "auto" or torch_dtype is None:
                pass  # torch_dtype is already a torch.dtype or "auto" or None
            elif isinstance(torch_dtype, str):  # it's a str, but not "auto"
                torch_dtype = getattr(torch, torch_dtype)
                model_init_kwargs["torch_dtype"] = torch_dtype
            else:
                raise ValueError(
                    "Invalid `torch_dtype` passed to `GRPOConfig`. Expected either 'auto' or a string representing "
                    f"a `torch.dtype` (e.g., 'float32'), but got {torch_dtype}."
                )
            # Disable caching if gradient checkpointing is enabled [not supported]
            model_init_kwargs["use_cache"] = (
                False if args.gradient_checkpointing else model_init_kwargs.get("use_cache")
            )
            model = AutoModelForCausalLM.from_pretrained(model, **model_init_kwargs)
        else:
            model_id = model.config._name_or_path
            if args.model_init_kwargs is not None:
                raise ValueError(
                    "You passed `model_init_kwargs` to the `GRPOConfig`, but your model is already instantiated. "
                    "This argument can only be used when the `model` argument is a string."
                )

        if False:
            if not is_peft_available():
                raise ImportError("PEFT is required to use `peft_config`. Run `pip install peft`.")
            model = model

        # Enable gradient checkpointing if requested
        if args.gradient_checkpointing:
            model = self._enable_gradient_checkpointing(model, args)

        # Processing class
        if processing_class is None:
            processing_class = AutoTokenizer.from_pretrained(model.config._name_or_path, padding_side="left")
        if processing_class.pad_token is None:
            processing_class.pad_token = processing_class.eos_token

        # Reward functions
        if not isinstance(reward_funcs, list):
            reward_funcs = [reward_funcs]
        self.reward_func_names = []
        for i, reward_func in enumerate(reward_funcs):
            if isinstance(reward_func, str):
                reward_funcs[i] = AutoModelForSequenceClassification.from_pretrained(
                    reward_func, num_labels=1, **model_init_kwargs
                )
            if isinstance(reward_funcs[i], nn.Module):  # Use Module over PretrainedModel for compat w/ compiled models
                self.reward_func_names.append(reward_funcs[i].config._name_or_path.split("/")[-1])
            else:
                self.reward_func_names.append(reward_funcs[i].__name__)
        self.reward_funcs = reward_funcs

        # Reward weights
        if args.reward_weights is not None:
            if len(args.reward_weights) != len(reward_funcs):
                raise ValueError(
                    f"Number of reward weights ({len(args.reward_weights)}) must match number of reward "
                    f"functions ({len(reward_funcs)})"
                )
            self.reward_weights = torch.tensor(args.reward_weights, dtype=torch.float32)
        else:
            self.reward_weights = torch.ones(len(reward_funcs), dtype=torch.float32)

        # Reward processing class
        if reward_processing_classes is None:
            reward_processing_classes = [None] * len(reward_funcs)
        elif not isinstance(reward_processing_classes, list):
            reward_processing_classes = [reward_processing_classes]
        else:
            if len(reward_processing_classes) != len(reward_funcs):
                raise ValueError("The number of reward processing classes must match the number of reward functions.")

        for i, (reward_processing_class, reward_func) in enumerate(zip(reward_processing_classes, reward_funcs)):
            if isinstance(reward_func, PreTrainedModel):
                if reward_processing_class is None:
                    reward_processing_class = AutoTokenizer.from_pretrained(reward_func.config._name_or_path)
                if reward_processing_class.pad_token_id is None:
                    reward_processing_class.pad_token = reward_processing_class.eos_token
                # The reward model computes the reward for the latest non-padded token in the input sequence.
                # So it's important to set the pad token ID to the padding token ID of the processing class.
                reward_func.config.pad_token_id = reward_processing_class.pad_token_id
                reward_processing_classes[i] = reward_processing_class
        self.reward_processing_classes = reward_processing_classes

        # Training arguments
        self.max_prompt_length = args.max_prompt_length
        self.max_completion_length = args.max_completion_length  # = |o_i| in the GRPO paper
        self.num_generations = args.num_generations  # = G in the GRPO paper
        self.temperature = args.temperature
        self.top_p = args.top_p
        self.top_k = args.top_k
        self.min_p = args.min_p
        self.repetition_penalty = args.repetition_penalty
        self.use_vllm = args.use_vllm
        self.vllm_mode = args.vllm_mode
        self.vllm_gpu_memory_utilization = args.vllm_gpu_memory_utilization  # only applies to colocation mode
        self.vllm_tensor_parallel_size = args.vllm_tensor_parallel_size  # only applies to colocation mode
        self.use_liger_loss = args.use_liger_loss
        self.loss_type = args.loss_type
        self.scale_rewards = args.scale_rewards
        self.mask_truncated_completions = args.mask_truncated_completions

        # Datasets
        self.shuffle_dataset = args.shuffle_dataset

        if (
            isinstance(train_dataset, IterableDataset)
            or isinstance(eval_dataset, IterableDataset)
            or (
                isinstance(eval_dataset, dict) and any(isinstance(ds, IterableDataset) for ds in eval_dataset.values())
            )
        ):
            # See https://github.com/huggingface/trl/issues/3213
            raise NotImplementedError(
                "Iterable datasets are not yet supported in GRPOTrainer. Please use a standard dataset instead."
            )

        # Multi-step
        self.num_iterations = args.num_iterations  # = 𝜇 in the GRPO paper
        self.epsilon_low = args.epsilon
        self.epsilon_high = args.epsilon_high if args.epsilon_high is not None else args.epsilon
        # Tracks the number of iterations [forward + backward passes], including those within a grad accum cycle
        self._step = 0
        # Buffer the batch to reuse generated outputs across multiple updates. For more details, see
        # `_get_train_sampler` and `_prepare_inputs`.
        self._buffered_inputs = None

        # The trainer estimates the number of FLOPs [floating-point operations] using the number of elements in the
        # input tensor associated with the key "input_ids". However, in GRPO, the sampled data does not include the
        # "input_ids" key. Instead, the available keys is "prompt". As a result, the trainer issues the warning:
        # "Could not estimate the number of tokens of the input, floating-point operations will not be computed." To
        # suppress this warning, we set the "estimate_tokens" key in the model's "warnings_issued" dictionary to True.
        # This acts as a flag to indicate that the warning has already been issued.
        model.warnings_issued["estimate_tokens"] = True

        super().__init__(
            model=model,
            args=args,
            data_collator=identity,  # No data collation is needed in GRPO
            train_dataset=train_dataset,
            eval_dataset=eval_dataset,
            processing_class=processing_class,
            callbacks=callbacks,
            optimizers=optimizers,
        )

        # Reference model
        self.beta = args.beta
        if self.beta == 0.0:
            # If beta is 0.0, the reference model is not needed
            self.ref_model = None
        elif is_peft_model(model):
            # If PEFT is used, the reference model is not needed since the adapter can be disabled
            # to revert to the initial model.
            self.ref_model = None
        else:
            # For deepspeed, fsdp or non-distributed models, create a reference model from scratch
            self.ref_model = AutoModelForCausalLM.from_pretrained(model_id, **model_init_kwargs)

        # Disable dropout in the models
        if args.disable_dropout:
            disable_dropout_in_model(model)
            if self.ref_model is not None:
                disable_dropout_in_model(self.ref_model)

        # Liger loss
        if self.use_liger_loss:
            if not is_liger_kernel_available():
                raise ImportError(
                    "Liger is required to use `liger_loss` as the GRPO loss. Run `pip install liger-kernel`."
                )
            # redirect the model.module forward to the model forward to ensure pre-forward hooks are called
            self._forward_redirection = _ForwardRedirection()

            self.liger_grpo_loss = LigerFusedLinearGRPOLoss(
                beta=self.beta,
                epsilon_low=self.epsilon_low,
                epsilon_high=self.epsilon_high,
                temperature=self.temperature,
                use_ref_model=self.beta != 0.0,
                loss_type=self.loss_type,
                max_completion_length=self.max_completion_length,
            )

        # Initialize the metrics
        self._metrics = {"train": defaultdict(list), "eval": defaultdict(list)}
        self._total_train_tokens = 0
        self.log_completions = args.log_completions
        self.wandb_log_unique_prompts = args.wandb_log_unique_prompts
        self.num_completions_to_print = args.num_completions_to_print
        # maxlen is set to the total number of forward passes per step. This value of `maxlen` ensures we log only the
        # final optimization step.
        maxlen = self.accelerator.num_processes * args.per_device_train_batch_size * args.steps_per_generation
        self._textual_logs = {
            "prompt": deque(maxlen=maxlen),
            "completion": deque(maxlen=maxlen),
            "rewards": defaultdict(lambda: deque(maxlen=maxlen)),
            "advantages": deque(maxlen=maxlen),
        }

        # Ensure each process receives a unique seed to prevent duplicate completions when generating with
        # transformers if num_generations exceeds per_device_train_batch_size. We could skip it if we use vLLM, but
        # it's safer to set it in all cases.
        set_seed(args.seed, device_specific=True)

        if self.use_vllm:
            if not is_vllm_available():
                raise ImportError(
                    "vLLM is not available and `use_vllm` is set to True. Please install vLLM with "
                    "`pip install vllm` to use it."
                )

            if self.vllm_mode == "server" and self.accelerator.is_main_process:
                if args.vllm_server_base_url is not None:
                    base_url = args.vllm_server_base_url
                else:
                    base_url = f"http://{args.vllm_server_host}:{args.vllm_server_port}"
                self.vllm_client = VLLMClient(base_url=base_url, connection_timeout=args.vllm_server_timeout)
                self.vllm_client.init_communicator()

            elif self.vllm_mode == "colocate":
                if not self.accelerator.num_processes % self.vllm_tensor_parallel_size == 0:
                    raise ValueError(
                        f"vllm_tensor_parallel_size ({self.vllm_tensor_parallel_size}) must divide world size "
                        f"({self.accelerator.num_processes}) evenly."
                    )

                if self.vllm_tensor_parallel_size > 1:
                    self.tp_group, _ = torch.distributed.new_subgroups_by_enumeration(
                        [
                            list(range(i * self.vllm_tensor_parallel_size, (i + 1) * self.vllm_tensor_parallel_size))
                            for i in range(self.accelerator.num_processes // self.vllm_tensor_parallel_size)
                        ]
                    )

                self.llm = model.vllm_engine
            self.guided_decoding_regex = args.vllm_guided_decoding_regex

            self._last_loaded_step = -1
            self.accelerator.wait_for_everyone()
        else:
            generation_kwargs = {
                "max_new_tokens": self.max_completion_length,
                "do_sample": True,
                "pad_token_id": processing_class.pad_token_id,
                "bos_token_id": processing_class.bos_token_id,
                "eos_token_id": processing_class.eos_token_id,
                "temperature": self.temperature,
                "top_p": self.top_p,
                "top_k": self.top_k,
                "min_p": self.min_p,
                "repetition_penalty": self.repetition_penalty,
                "cache_implementation": args.cache_implementation,
            }
            if args.generation_kwargs is not None:
                generation_kwargs.update(args.generation_kwargs)
            self.generation_config = GenerationConfig(**generation_kwargs)

        # Gradient accumulation requires scaled loss. Normally, loss scaling in the parent class depends on whether the
        # model accepts loss-related kwargs. Since we compute our own loss, this check is irrelevant. We set
        # self.model_accepts_loss_kwargs to False to enable scaling.
        self.model_accepts_loss_kwargs = False

        # Add tags to the model
        self.model.add_model_tags(self._tag_names)

        if self.ref_model is not None:
            if self.is_deepspeed_enabled:
                self.ref_model = prepare_deepspeed(self.ref_model, self.accelerator)
            elif self.is_fsdp_enabled:
                self.ref_model = prepare_fsdp(self.ref_model, self.accelerator)
            else:
                self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)

        if args.sync_ref_model:
            self.add_callback(SyncRefModelCallback(ref_model=self.ref_model, accelerator=self.accelerator))

        for i, reward_func in enumerate(self.reward_funcs):
            if isinstance(reward_func, PreTrainedModel):
                if self.is_deepspeed_enabled:
                    self.reward_funcs[i] = prepare_deepspeed(reward_func, self.accelerator)
                else:
                    # set device placement to True to make `prepare_model` move `reward_func` to device when using fsdp
                    self.reward_funcs[i] = self.accelerator.prepare_model(
                        reward_func, evaluation_mode=True, device_placement=True
                    )

    def _set_signature_columns_if_needed(self):
        # If `self.args.remove_unused_columns` is True, non-signature columns are removed.
        # By default, this method sets `self._signature_columns` to the model's expected inputs.
        # In GRPOTrainer, we preprocess data, so using the model's signature columns doesn't work.
        # Instead, we set them to the columns expected by the `training_step` method, hence the override.
        if self._signature_columns is None:
            self._signature_columns = ["prompt"]

    # This method overrides `Trainer.get_train_dataloader` to support our custom batching strategy.
    # Instead of returning a standard per-step batch (i.e., `per_device_batch_size), our dataloader loads an
    # *generation* batch (i.e., `per_device_batch_size × steps_per_generation`). This allows us to generate completions
    # once every steps_per_generation step—rather than once per accumulation step—which is significantly more
    # efficient. The only change from the original implementation is multiplying the batch size by
    # `steps_per_generation`. Thus, `_prepare_inputs` is called with this *generation* batch, and it handles the
    # splitting internally.
    # Maintenance note: This method is a copy-paste of the original `Trainer.get_train_dataloader` with only one line
    # modification. As a result, some parts of the method aren't relevant to GRPO, but we keep them to stay one line
    # apart from the super method, ensuring easier maintenance in the future.
    def get_train_dataloader(self):
        if self.train_dataset is None:
            raise ValueError("Trainer: training requires a train_dataset.")

        train_dataset = self.train_dataset
        data_collator = self.data_collator
        if is_datasets_available() and isinstance(train_dataset, datasets.Dataset):
            train_dataset = self._remove_unused_columns(train_dataset, description="training")
        else:
            data_collator = self._get_collator_with_removed_columns(data_collator, description="training")

        dataloader_params = {
            "batch_size": self._train_batch_size * self.args.steps_per_generation,  # < this is the change
            "collate_fn": data_collator,
            "num_workers": self.args.dataloader_num_workers,
            "pin_memory": self.args.dataloader_pin_memory,
            "persistent_workers": self.args.dataloader_persistent_workers,
        }

        if not isinstance(train_dataset, torch.utils.data.IterableDataset):
            dataloader_params["sampler"] = self._get_train_sampler()
            dataloader_params["drop_last"] = self.args.dataloader_drop_last
            if version.parse(transformers.__version__) >= version.parse("4.52.0"):
                # from transformers 4.52.0, the `seed_worker` requires the `num_workers` and `rank` arguments
                dataloader_params["worker_init_fn"] = partial(
                    seed_worker, num_workers=self.args.dataloader_num_workers, rank=self.args.process_index
                )
            else:
                dataloader_params["worker_init_fn"] = seed_worker
            dataloader_params["prefetch_factor"] = self.args.dataloader_prefetch_factor

        return self.accelerator.prepare(DataLoader(train_dataset, **dataloader_params))

    def _get_train_sampler(self, dataset: Optional[Dataset] = None) -> Sampler:
        # Returns a sampler that
        # 1. ensures each prompt is repeated across multiple processes. This guarantees that identical prompts are
        #    distributed to different GPUs, allowing rewards to be computed and normalized correctly within each prompt
        #    group. Using the same seed across processes ensures consistent prompt assignment, preventing discrepancies
        #    in group formation.
        # 2. repeats the batch multiple times to allow reusing generations across multiple updates. Refer to
        #    _prepare_inputs to see how the generations are stored and reused.

        # In the following figure, the values are the prompt indices. The first row shows the first sampled batch, the
        # second row shows the second sampled batch, and so on.
        #
        #                                      |   GPU 0  |   GPU 1  |
        #
        #                 global_step   step    <-───>  num_generations=2
        #                                       <-───────> per_device_train_batch_size=3
        #  grad_accum    ▲  ▲  0          0     0   0   1   1   2   2   <- Generate for the first `steps_per_generation` (prompts 0 to 11); store the completions; use the first slice to compute the loss
        #     =2         ▼  |  0          1     3   3   4   4   5   5   <- Take the stored generations and use the second slice to compute the loss
        #                   |
        #                   |  1          2     6   6   7   7   8   8   <- Take the stored generations and use the third slice to compute the loss
        #  steps_per_gen=4  ▼  1          3     9   9  10  10  11  11   <- Take the stored generations and use the fourth slice to compute the loss
        #
        #                      2          4    12  12  13  13  14  14   <- Generate for the second `steps_per_generation` (prompts 12 to 23); store the completions; use the first slice to compute the loss
        #                      2          5    15  15  16  16  17  17   <- Take the stored generations and use the second slice to compute the loss
        #                                          ...
        if dataset is None:
            dataset = self.train_dataset
        return RepeatSampler(
            data_source=dataset,
            mini_repeat_count=self.num_generations,
            batch_size=self.args.generation_batch_size // self.num_generations,
            repeat_count=self.num_iterations * self.args.steps_per_generation,
            shuffle=self.shuffle_dataset,
            seed=self.args.seed,
        )

    def _get_eval_sampler(self, eval_dataset) -> Sampler:
        # See _get_train_sampler for an explanation of the sampler.
        return RepeatSampler(
            data_source=eval_dataset,
            mini_repeat_count=self.num_generations,
            seed=self.args.seed,
        )

    def _enable_gradient_checkpointing(self, model: PreTrainedModel, args: GRPOConfig) -> PreTrainedModel:
        """Enables gradient checkpointing for the model."""
        # Ensure use_cache is disabled
        model.config.use_cache = False

        # Enable gradient checkpointing on the base model for PEFT
        if is_peft_model(model):
            model.base_model.gradient_checkpointing_enable()
        # Enable gradient checkpointing for non-PEFT models
        else:
            model.gradient_checkpointing_enable()

        gradient_checkpointing_kwargs = args.gradient_checkpointing_kwargs or {}
        use_reentrant = (
            "use_reentrant" not in gradient_checkpointing_kwargs or gradient_checkpointing_kwargs["use_reentrant"]
        )

        if use_reentrant:
            model.enable_input_require_grads()

        return model

    @profiling_decorator
    def _get_last_hidden_state(self, unwrapped_model, input_ids, attention_mask, logits_to_keep=None):
        if is_peft_model(unwrapped_model):
            unwrapped_model = unwrapped_model.base_model.model
        last_hidden_state = unwrapped_model.model(input_ids=input_ids, attention_mask=attention_mask).last_hidden_state
        last_hidden_state = last_hidden_state[:, :-1, :]  # (B, L-1, H)
        if logits_to_keep is not None:
            last_hidden_state = last_hidden_state[:, -logits_to_keep:, :]  # (B, logits_to_keep, H)
        return last_hidden_state

    # Get the per-token log probabilities for the completions for the model and the reference model
    def _get_per_token_logps(self, model, input_ids, attention_mask, logits_to_keep):
        if True: # os.environ.get('UNSLOTH_USE_NEW_MODEL', '0') == '0':
            return None # Unsloth efficient GRPO
        # Otherwise, calculate normally:
        if not hasattr(self, '_autocast_dtype'):
            self._autocast_dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16
            if os.environ.get('UNSLOTH_FORCE_FLOAT32', '0') == '1': self._autocast_dtype = torch.float16

        os.environ["UNSLOTH_RETURN_HIDDEN_STATES"] = "1"
        with torch.amp.autocast(device_type = DEVICE_TYPE, dtype = self._autocast_dtype):
            # We add 1 to `logits_to_keep` because the last logits of the sequence is later excluded
            logits = model(
                input_ids = input_ids,
                attention_mask = attention_mask,
                logits_to_keep = logits_to_keep + 1,
            ).logits
            # logits = logits[:, :-1, :]  # (B, L-1, V), exclude the last logit: it corresponds to the next token pred
            return logits
            # input_ids = input_ids[:, -logits_to_keep:]
            # For transformers<=4.48, logits_to_keep argument isn't supported, so here we drop logits ourselves.
            # See https://github.com/huggingface/trl/issues/2770
            # logits = logits[:, -logits_to_keep:]
            # return logits
            # See https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo#policy-training-implementation-details
            # logits = logits / self.temperature
            # logps = selective_log_softmax(logits, input_ids)

            # row_indices, col_indices = torch.where(logps < -20)

            # # Method 1: Check if tensors have elements
            # if len(row_indices) > 0 and len(col_indices) > 0:
            #     breakpoint()  # Breakpoint triggered here
            #     print("Found high values!")
            # return  logps #  compute logprobs for the input tokens
        pass

    def _sync_fsdp_params_to_vllm(self, module: nn.Module, prefix: str = "", visited=None):
        """Memory-efficient post-order traversal of FSDP modules to extract full parameters and sync with vLLM."""
        if visited is None:
            visited = set()

        for child_name, child_module in module.named_children():
            child_prefix = f"{prefix}.{child_name}" if prefix else child_name
            self._sync_fsdp_params_to_vllm(
                child_module, prefix=child_prefix, visited=visited
            )  # recurse into the child

        if isinstance(module, FSDP):
            with FSDP.summon_full_params(module, recurse=False, writeback=False):
                for param_name, param in module.named_parameters():
                    full_name = f"{prefix}.{param_name}" if prefix else param_name
                    for extra in ("_fsdp_wrapped_module.", "_checkpoint_wrapped_module."):
                        full_name = full_name.replace(extra, "")

                    if full_name in visited:
                        continue  # skip FSDP subtrees already traversed
                    visited.add(full_name)

                    if self.vllm_mode == "server" and self.accelerator.is_main_process:
                        self.vllm_client.update_named_param(full_name, param.data)
                    elif self.vllm_mode == "colocate":

                        pass

                        pass

    def _move_model_to_vllm(self, *args, **kwargs): return None

    @profiling_decorator
    def _prepare_inputs(
        self, generation_batch: dict[str, Union[torch.Tensor, Any]]
    ) -> dict[str, Union[torch.Tensor, Any]]:
        # Prepares inputs for model training/evaluation by managing completion generation and batch handling.
        # During training:
        #   - Receives the local generation batch (Per-GPU batch size × steps per generation)
        #     from the modified training dataloader instead of the standard local batch
        #   - Generates completions once for the entire generation batch and splits it into batches of size
        #     `per_device_train_batch_size`
        #   - Buffers these completions and returns the appropriate slice for the current accumulation step
        #   - Optimizes by regenerating completions only periodically (every steps_per_generation * num_iterations)
        # During evaluation:
        #   - The input is treated as a standard local batch (no accumulation, no multiple iterations)
        #   - Completions are generated for each batch without buffering or reuse
        # Returns a single local batch in both cases.
        if hasattr(self, 'llm'):
           if getattr(self.llm.llm_engine.vllm_config.model_config, 'enable_sleep_mode', False):
               self.llm.wake_up()

        mode = "train" if self.model.training else "eval"
        if mode == "train":
            generate_every = self.args.steps_per_generation * self.num_iterations
            if self._step % generate_every == 0 or self._buffered_inputs is None:
                # self._buffered_inputs=None can occur when resuming from a checkpoint
                generation_batch = self._generate_and_score_completions(generation_batch)
                generation_batch = shuffle_tensor_dict(generation_batch)
                self._buffered_inputs = split_tensor_dict(generation_batch, self.args.steps_per_generation)
            inputs = self._buffered_inputs[self._step % self.args.steps_per_generation]
            self._step += 1
        else:
            # In evaluation, there is neither batch grouping for generation, nor multiple iterations, hence
            # local generation batch == local eval batch
            inputs = self._generate_and_score_completions(generation_batch)
        if hasattr(self, 'llm'):
            if getattr(self.llm.llm_engine.vllm_config.model_config, 'enable_sleep_mode', False):
                self.llm.sleep(os.environ.get('VLLM_SLEEP_MODE', 1))
        return inputs

    @profiling_decorator
    def _calculate_rewards(self, inputs, prompts, completions, completion_ids_list):
        device = self.accelerator.device
        rewards_per_func = torch.zeros(len(prompts), len(self.reward_funcs), device=device)

        # Repeat all input columns (but "prompt", "completion", and "completion_ids") to match the num of generations
        keys = [key for key in inputs[0] if key not in ["prompt", "completion", "completion_ids"]]
        reward_kwargs = {key: [example[key] for example in inputs] for key in keys}

        for i, (reward_func, reward_processing_class, reward_func_name) in enumerate(
            zip(self.reward_funcs, self.reward_processing_classes, self.reward_func_names)
        ):
            with profiling_context(self, reward_func_name):
                if isinstance(reward_func, nn.Module):  # Module (no PretrainedModel) for compat with compiled models
                    if is_conversational(inputs[0]):
                        messages = [{"messages": p + c} for p, c in zip(prompts, completions)]
                        texts = [apply_chat_template(x, reward_processing_class)["text"] for x in messages]
                    else:
                        texts = [p + c for p, c in zip(prompts, completions)]
                    reward_inputs = reward_processing_class(
                        text=texts, return_tensors="pt", padding=True, padding_side="right", add_special_tokens=False
                    )
                    reward_inputs = super()._prepare_inputs(reward_inputs)
                    with torch.inference_mode():
                        rewards_per_func[:, i] = reward_func(**reward_inputs).logits[:, 0]  # Shape (B*G,)
                else:
                    output_reward_func = reward_func(
                        prompts=prompts, completions=completions, completion_ids=completion_ids_list, **reward_kwargs
                    )
                    # Convert None values to NaN
                    output_reward_func = [reward if reward is not None else torch.nan for reward in output_reward_func]

                    rewards_per_func[:, i] = torch.tensor(output_reward_func, dtype=torch.float32, device=device)

        # If all reward functions return None for a given row, issue a detailed warning
        if torch.isnan(rewards_per_func).all(dim=1).any():
            nan_row_idx = torch.isnan(rewards_per_func).all(dim=1).nonzero(as_tuple=True)[0][0]
            row_reward_kwargs = {key: value[nan_row_idx] for key, value in reward_kwargs.items()}
            row_reward_kwargs["prompt"] = prompts[nan_row_idx]
            row_reward_kwargs["completion"] = completions[nan_row_idx]
            warnings.warn(
                f"All reward functions returned None for the following kwargs: {row_reward_kwargs}. "
                "Please ensure that at least one reward function returns a valid reward."
            )

        # Gather the reward per function: this part is crucial, because the rewards are normalized per group and the
        # completions may be distributed across processes
        rewards_per_func = gather(rewards_per_func)
        return rewards_per_func

    def _generate_and_score_completions(
        self, inputs: list[dict[str, Union[torch.Tensor, Any]]]
    ) -> dict[str, Union[torch.Tensor, Any]]:
        device = self.accelerator.device
        mode = "train" if self.model.training else "eval"

        prompts = [x["prompt"] for x in inputs]
        prompts_text = [maybe_apply_chat_template(example, self.processing_class)["prompt"] for example in inputs]
        prompt_inputs = self.processing_class(
            text=prompts_text, return_tensors="pt", padding=True, padding_side="left", add_special_tokens=False
        )
        prompt_inputs = super()._prepare_inputs(prompt_inputs)
        prompt_ids, prompt_mask = prompt_inputs["input_ids"], prompt_inputs["attention_mask"]
        if self.max_prompt_length is not None:
            # If max_prompt_length is set, we trim the prompt to keep only the last `max_prompt_length` tokens.
            # Then we decode those tokens back into text. We manually remove leading pad tokens from the decoded text,
            # because we can't use `skip_special_tokens=True` (some special tokens are still needed for generation).
            prompt_ids = prompt_ids[:, -self.max_prompt_length :]
            prompt_mask = prompt_mask[:, -self.max_prompt_length :]
            prompts_text = self.processing_class.batch_decode(
                prompt_ids, skip_special_tokens=False, clean_up_tokenization_spaces=False
            )
            pad_token = self.processing_class.pad_token
            def strip_leading_tokens(text):
                while text.startswith(pad_token):
                    text = text.removeprefix(pad_token)
                return text

            if pad_token is not None:
                prompts_text = [
                    strip_leading_tokens(text) for text in prompts_text
                ]

        # Generate completions using either vLLM or regular generation
        if self.use_vllm:
            # First, update the vLLM weights if needed
            if self.state.global_step != self._last_loaded_step:
                self._move_model_to_vllm()
                self._last_loaded_step = self.state.global_step

            # Generate completions using vLLM: gather all prompts and use them in a single call in the main process
            if self.vllm_mode == "server":
                all_prompts_text = gather_object(prompts_text)
                if self.accelerator.is_main_process:
                    # Since 'prompts' contains 'num_generations' duplicates, we first take unique prompts, and generate
                    # num_generations outputs for each one. This is faster than generating outputs for each duplicate
                    # prompt individually.
                    ordered_set_of_prompts = all_prompts_text[:: self.num_generations]
                    with profiling_context(self, "vLLM.generate"):
                        completion_ids = self.vllm_client.generate(
                            prompts=ordered_set_of_prompts,
                            n=self.num_generations,
                            repetition_penalty=self.repetition_penalty,
                            temperature=self.temperature,
                            top_p=self.top_p,
                            top_k=-1 if self.top_k is None else self.top_k,
                            min_p=0.0 if self.min_p is None else self.min_p,
                            max_tokens=self.max_completion_length,
                            guided_decoding_regex=self.guided_decoding_regex,
                            generation_kwargs=self.args.generation_kwargs,
                        )
                else:
                    completion_ids = [None] * len(all_prompts_text)
                # Broadcast the completions from the main process to all processes, ensuring each process receives its
                # corresponding slice.
                completion_ids = broadcast_object_list(completion_ids, from_process=0)
                process_slice = slice(
                    self.accelerator.process_index * len(prompts),
                    (self.accelerator.process_index + 1) * len(prompts),
                )
                completion_ids = completion_ids[process_slice]

            # Generate completions using colocated vLLM instances: each device holds vLLM copy and work on their own batch of prompts
            elif self.vllm_mode == "colocate":
                if self.guided_decoding_regex:
                    guided_decoding = GuidedDecodingParams(backend="outlines", regex=self.guided_decoding_regex)
                else:
                    guided_decoding = None

                generation_kwargs = {
                    "n": 1,  # vLLM on each GPU generates only 1 in colocate mode
                    "repetition_penalty": self.repetition_penalty,
                    "temperature": self.temperature,
                    "top_p": self.top_p,
                    "top_k": -1 if self.top_k is None else self.top_k,
                    "min_p": 0.0 if self.min_p is None else self.min_p,
                    "max_tokens": self.max_completion_length,
                    "guided_decoding": guided_decoding,
                }
                if self.args.generation_kwargs is not None:
                    generation_kwargs.update(self.args.generation_kwargs)
                sampling_params = SamplingParams(**generation_kwargs)

                if self.vllm_tensor_parallel_size > 1:
                    # Gather prompts from all ranks in the TP group and flatten.
                    # Each rank starts with its own prompts; after gathering, all ranks see the full group set.
                    orig_size = len(prompts_text)
                    gathered_prompts = [None for _ in range(self.vllm_tensor_parallel_size)]
                    torch.distributed.all_gather_object(gathered_prompts, prompts_text, group=self.tp_group)
                    all_prompts_text = [p for sublist in gathered_prompts for p in sublist]
                else:
                    all_prompts_text = prompts_text

                with profiling_context(self, "vLLM.generate"):
                    all_outputs = self.llm.generate(all_prompts_text, sampling_params=sampling_params, use_tqdm=False, lora_request = self.model.load_lora('grpo_trainer_lora_model', load_tensors = True))

                completion_ids = [output.token_ids for outputs in all_outputs for output in outputs.outputs]

                if self.vllm_tensor_parallel_size > 1:
                    # Slice completions for this rank within its TP group.
                    # Each rank generates all outputs — we keep only our share.
                    local_rank_in_group = torch.distributed.get_rank(group=self.tp_group)
                    tp_slice = slice(local_rank_in_group * orig_size, (local_rank_in_group + 1) * orig_size)
                    completion_ids = completion_ids[tp_slice]

            # Pad the completions, and concatenate them with the prompts
            completion_ids = [torch.tensor(ids, device=device) for ids in completion_ids]
            completion_ids = pad(completion_ids, padding_value=self.processing_class.pad_token_id)
            prompt_completion_ids = torch.cat([prompt_ids, completion_ids], dim=1)
        else:
            # Regular generation path
            with unwrap_model_for_generation(
                self.model_wrapped, self.accelerator, gather_deepspeed3_params=self.args.ds3_gather_for_generation
            ) as unwrapped_model:
                with (
                    FSDP.summon_full_params(self.model_wrapped, recurse=False)
                    if self.is_fsdp_enabled
                    else nullcontext()
                ):
                    prompt_completion_ids = unwrapped_model.generate(
                        prompt_ids, attention_mask=prompt_mask, generation_config=self.generation_config
                    )

            # Compute prompt length and extract completion ids
            prompt_length = prompt_ids.size(1)
            prompt_ids = prompt_completion_ids[:, :prompt_length]
            completion_ids = prompt_completion_ids[:, prompt_length:]

        # Mask everything after the first EOS token
        is_eos = completion_ids == self.processing_class.eos_token_id
        eos_idx = torch.full((is_eos.size(0),), is_eos.size(1), dtype=torch.long, device=device)
        eos_idx[is_eos.any(dim=1)] = is_eos.int().argmax(dim=1)[is_eos.any(dim=1)]
        sequence_indices = torch.arange(is_eos.size(1), device=device).expand(is_eos.size(0), -1)
        completion_mask = (sequence_indices <= eos_idx.unsqueeze(1)).int()

        # Convert tensor to a list of lists of token IDs. This will be passed to the reward function, avoiding the need
        # to re-tokenize completions if the reward is computed from tokens.
        completion_ids_list = [
            [id.item() for id, m in zip(row, mask_row) if m] for row, mask_row in zip(completion_ids, completion_mask)
        ]

        # Sum along sequence dimension (dim=1) to get completion length per sequence, used for logging
        completion_lengths = completion_mask.sum(1)

        # If mask_truncated_completions is enabled, zero out truncated completions in completion_mask
        if self.mask_truncated_completions:
            truncated_completions = ~is_eos.any(dim=1)
            completion_mask = completion_mask * (~truncated_completions).unsqueeze(1).int()

        # Concatenate prompt_mask with completion_mask for logit computation
        attention_mask = torch.cat([prompt_mask, completion_mask], dim=1)  # (B, P+C)

        logits_to_keep = completion_ids.size(1)  # we only need to compute the logits for the completion tokens
        batch_size = self.args.per_device_train_batch_size if mode == "train" else self.args.per_device_eval_batch_size

        with torch.no_grad():
            # When using num_iterations == 1 and steps_per_generation <= gradient_accumulation_steps
            # old_per_token_logps == per_token_logps, so we can skip it's computation here, and use
            # per_token_logps.detach() instead.
            if self.num_iterations > 1 or self.args.steps_per_generation > self.args.gradient_accumulation_steps:
                old_per_token_logps = self._get_per_token_logps(
                    self.model, prompt_completion_ids, attention_mask, logits_to_keep, batch_size
                )
            else:
                old_per_token_logps = None

            # Compute the per-token log probabilities for the reference model
            if self.beta != 0.0:
                if self.ref_model is not None:
                    ref_per_token_logps = self._get_per_token_logps(
                        self.ref_model, prompt_completion_ids, attention_mask, logits_to_keep
                    )
                else:
                    with self.accelerator.unwrap_model(self.model).disable_adapter():
                        ref_per_token_logps = self._get_per_token_logps(
                            self.model, prompt_completion_ids, attention_mask, logits_to_keep
                        )
            else:
                ref_per_token_logps = None

        # Decode the generated completions
        completions_text = self.processing_class.batch_decode(completion_ids, skip_special_tokens=True)
        if is_conversational(inputs[0]):
            completions = []
            for prompt, completion in zip(prompts, completions_text):
                bootstrap = prompt.pop()["content"] if prompt[-1]["role"] == "assistant" else ""
                completions.append([{"role": "assistant", "content": bootstrap + completion}])
        else:
            completions = completions_text

        # Calculate rewards for each reward function. rewards_per_func aggregates rewards across all processes. This is
        # important because rewards will be normalized per group, and completions are distributed. We will later slice
        # rewards_per_func to extract each process's subset.
        rewards_per_func = self._calculate_rewards(inputs, prompts, completions, completion_ids_list)

        # Apply weights to each reward function's output and sum
        rewards = (rewards_per_func * self.reward_weights.to(device).unsqueeze(0)).nansum(dim=1)

        # Compute grouped-wise rewards
        mean_grouped_rewards = rewards.view(-1, self.num_generations).mean(dim=1)
        std_grouped_rewards = rewards.view(-1, self.num_generations).std(dim=1)
        is_std_zero = torch.isclose(std_grouped_rewards, torch.zeros_like(std_grouped_rewards))

        # Normalize the rewards to compute the advantages
        mean_grouped_rewards = mean_grouped_rewards.repeat_interleave(self.num_generations, dim=0)
        std_grouped_rewards = std_grouped_rewards.repeat_interleave(self.num_generations, dim=0)
        advantages = rewards - mean_grouped_rewards
        if self.scale_rewards:
            advantages = advantages / (std_grouped_rewards + 1e-4)

        # Slice to keep only the local part of the data
        process_slice = slice(
            self.accelerator.process_index * len(prompts),
            (self.accelerator.process_index + 1) * len(prompts),
        )
        all_process_advantages = advantages.clone()  # keep the aggregated advantages for logging
        advantages = advantages[process_slice]

        # Log the metrics
        if mode == "train":
            self.state.num_input_tokens_seen += self.accelerator.gather(attention_mask.sum()).sum().item()
        self._metrics[mode]["num_tokens"] = [self.state.num_input_tokens_seen]

        # Log completion lengths, mean, min, max
        agg_completion_lengths = self.accelerator.gather(completion_lengths)
        self._metrics[mode]["completions/mean_length"].append(agg_completion_lengths.float().mean().item())
        self._metrics[mode]["completions/min_length"].append(agg_completion_lengths.float().min().item())
        self._metrics[mode]["completions/max_length"].append(agg_completion_lengths.float().max().item())

        # Identify sequences that terminated with EOS and log their lengths
        agg_terminated_with_eos = self.accelerator.gather(is_eos.any(dim=1))
        term_completion_lengths = agg_completion_lengths[agg_terminated_with_eos]
        clipped_completions_ratio = 1 - len(term_completion_lengths) / len(agg_completion_lengths)
        self._metrics[mode]["completions/clipped_ratio"].append(clipped_completions_ratio)
        if len(term_completion_lengths) == 0:  # edge case where no terminated sequences are found
            term_completion_lengths = torch.zeros(1, device=device)
        self._metrics[mode]["completions/mean_terminated_length"].append(term_completion_lengths.float().mean().item())
        self._metrics[mode]["completions/min_terminated_length"].append(term_completion_lengths.float().min().item())
        self._metrics[mode]["completions/max_terminated_length"].append(term_completion_lengths.float().max().item())

        # Calculate mean reward per function, but only for samples where the function was applied (non-NaN values)
        for i, reward_func_name in enumerate(self.reward_func_names):
            mean_rewards = torch.nanmean(rewards_per_func[:, i]).item()
            self._metrics[mode][f"rewards/{reward_func_name}/mean"].append(mean_rewards)
            std_rewards = nanstd(rewards_per_func[:, i]).item()
            self._metrics[mode][f"rewards/{reward_func_name}/std"].append(std_rewards)
        self._metrics[mode]["reward"].append(mean_grouped_rewards.mean().item())
        self._metrics[mode]["reward_std"].append(std_grouped_rewards.mean().item())
        self._metrics[mode]["frac_reward_zero_std"].append(is_std_zero.float().mean().item())

        # Log prompt and completion texts
        self._textual_logs["prompt"].extend(gather_object(prompts_text))
        self._textual_logs["completion"].extend(gather_object(completions_text))
        for i, name in enumerate(self.reward_func_names):
            self._textual_logs["rewards"][name].extend(rewards_per_func[:, i].tolist())
        self._textual_logs["advantages"].extend(all_process_advantages.tolist())

        return {
            "prompt_ids": prompt_ids,
            "prompt_mask": prompt_mask,
            "completion_ids": completion_ids,
            "completion_mask": completion_mask,
            "advantages": advantages,
            "old_per_token_logps": old_per_token_logps,
            "ref_per_token_logps": ref_per_token_logps,
        }

    def compute_liger_loss(self, unwrapped_model, inputs):
        # Compute the per-token log probabilities for the model
        prompt_ids, prompt_mask = inputs["prompt_ids"], inputs["prompt_mask"]
        completion_ids, completion_mask = inputs["completion_ids"], inputs["completion_mask"]
        input_ids = torch.cat([prompt_ids, completion_ids], dim=1)
        attention_mask = torch.cat([prompt_mask, completion_mask], dim=1)
        logits_to_keep = completion_ids.size(1)  # we only need to compute the logits for the completion tokens

        # get the last hidden state of the model
        last_hidden_state = self._get_last_hidden_state(unwrapped_model, input_ids, attention_mask, logits_to_keep)

        # compute loss and metrics using liger grpo loss
        loss, metrics = self.liger_grpo_loss(
            _input=last_hidden_state,
            lin_weight=unwrapped_model.lm_head.weight,
            selected_token_ids=completion_ids,
            attention_mask=completion_mask,
            advantages=inputs["advantages"],
            bias=unwrapped_model.lm_head.bias,
            old_per_token_logps=inputs["old_per_token_logps"],
            ref_per_token_logps=inputs["ref_per_token_logps"],
        )
        # Extract metrics from the liger_grpo_loss output
        # KL divergence is the first metric when beta is non-zero
        mean_kl = metrics[0] if self.beta != 0.0 else None
        clip_ratio = metrics[-1]

        mode = "train" if self.model.training else "eval"
        if self.beta != 0.0:
            self._metrics[mode]["kl"].append(self.accelerator.gather(mean_kl).mean().item())
        self._metrics[mode]["clip_ratio"].append(self.accelerator.gather(clip_ratio).mean().item())
        return loss

    def compute_loss(self, model, inputs, return_outputs = False, num_items_in_batch = None):
        if return_outputs:
            raise ValueError("The GRPOTrainer does not support returning outputs")
        # Compute the per-token log probabilities for the model

        prompt_ids, prompt_mask = inputs["prompt_ids"], inputs["prompt_mask"]
        completion_ids, completion_mask = inputs["completion_ids"], inputs["completion_mask"]
        input_ids = torch.cat([prompt_ids, completion_ids], dim=1)
        bsz, qlen = input_ids.shape
        attention_mask = torch.cat([prompt_mask, completion_mask], dim=1)
        # attention_mask = None
        logits_to_keep = completion_ids.size(1)  # we only need to compute the logits for the completion tokens
        _input_ids = input_ids
        _logits_to_keep = logits_to_keep

        get_logps_func = \
            lambda model, input_ids, attention_mask, logits_to_keep, batch_size=None, compute_entropy=False: \
            self._get_per_token_logps(model, input_ids, attention_mask, logits_to_keep) \
            if hasattr(self, "_get_per_token_logps") else \
            self._get_per_token_logps_and_entropies(model, input_ids, attention_mask, logits_to_keep, batch_size, compute_entropy)['logps']

        per_token_logps = get_logps_func(model, input_ids, attention_mask, logits_to_keep)

        # Compute the KL divergence between the model and the reference model
        # _prepare_inputs doesn't return reference log probs anymore. We need to calculate it ourselves.
        # https://github.com/huggingface/trl/blob/05bc43e960396581e458195b8388efe6b82cae1f/trl/trainer/grpo_trainer.py#L1328
        if self.beta != 0.0:
            with torch.inference_mode(), model.disable_adapter():
                ref_per_token_logps = per_token_logps = get_logps_func(model, input_ids, attention_mask, logits_to_keep)
        else:
            ref_per_token_logps = None
        # per_token_kl = torch.exp(ref_per_token_logps - per_token_logps) - (ref_per_token_logps - per_token_logps) - 1
        # x - x.detach() allows for preserving gradients from x
        advantages = inputs["advantages"]
        # per_token_loss = torch.exp(per_token_logps - per_token_logps.detach()) * advantages.unsqueeze(1)
        # per_token_loss = -(per_token_loss - self.beta * per_token_kl)
        # loss = ((per_token_loss * completion_mask).sum(dim=1) / completion_mask.sum(dim=1)).mean()
        old_hidden_states = inputs.get("old_per_token_logps", None)
        input_ids = input_ids[:, -logits_to_keep:]

        # Get logit softcapping and logit scale
        logit_softcapping = getattr(model.config, "final_logit_softcapping", 0) # Gemma
        if logit_softcapping is None: logit_softcapping = 0
        logit_scale_multiply = getattr(model.config, "logit_scale", 0) # Cohere
        if logit_scale_multiply is None: logit_scale_multiply = 0
        logit_scale_divide = getattr(model.config, "logits_scaling", 0) # Granite
        if logit_scale_divide is None: logit_scale_divide = 0
        if per_token_logps is not None:

            if ref_per_token_logps is not None:
                ref_per_token_logps = ref_per_token_logps[:, :-1, :] # (B, L-1, V), exclude the last logit: it corresponds to the next token pred
            per_token_logps = per_token_logps[:, :-1, :] # (B, L-1, V), exclude the last logit: it corresponds to the next token pred

            loss, completion_length, mean_kl = grpo_compute_loss_slow(
                ref_per_token_logps,
                per_token_logps,
                old_hidden_states,
                input_ids,
                completion_mask,
                self.beta,
                advantages,
                loss_type = self.args.loss_type,
                epsilon_low = self.epsilon_low,
                epsilon_high = self.epsilon_high,
                max_completion_length = self.args.max_completion_length,
                delta = self.args.delta,
                temperature = self.args.temperature,
                logit_softcapping = logit_softcapping,
                logit_scale_multiply = logit_scale_multiply,
                logit_scale_divide = logit_scale_divide,
            )
        else:
            if hasattr(self.args, "loss_type"):
                loss, completion_length, mean_kl = grpo_accumulated_loss(
                    trainer = self,
                    input_ids = _input_ids,
                    logits_to_keep = logits_to_keep,
                    completion_mask = completion_mask,
                    advantages = advantages,
                    old_hidden_states = old_hidden_states,
                    n_chunks = self.args.unsloth_num_chunks,
                    loss_type = self.args.loss_type,
                    epsilon_low = self.epsilon_low,
                    epsilon_high = self.epsilon_high,
                    max_completion_length = self.args.max_completion_length,
                    delta = self.args.delta,
                    temperature = self.args.temperature,
                    logit_softcapping = logit_softcapping,
                    logit_scale_multiply = logit_scale_multiply,
                    logit_scale_divide = logit_scale_divide,
                    attention_mask = attention_mask,
                )
            else:
                # to ensure backwards compatibility with trl 0.15.2 and maybe even 0.17
                loss, completion_length, mean_kl = grpo_accumulated_loss(
                    trainer = self,
                    input_ids = _input_ids,
                    logits_to_keep = logits_to_keep,
                    completion_mask = completion_mask,
                    advantages = advantages,
                    old_hidden_states = old_hidden_states,
                    n_chunks = self.args.unsloth_num_chunks,
                    temperature = self.args.temperature,
                    logit_softcapping = logit_softcapping,
                    logit_scale_multiply = logit_scale_multiply,
                    logit_scale_divide = logit_scale_divide,
                    attention_mask = attention_mask,
                )
            pass
        pass
        # Log the metrics
        # completion_length = self.accelerator.gather_for_metrics(completion_mask.sum(1)).float().mean().item()
        # mean_kl = ((per_token_kl * completion_mask).sum(dim=1) / completion_mask.sum(dim=1)).mean()
        # self._metrics["kl"].append(self.accelerator.gather_for_metrics(mean_kl).mean().item())
        if "train" in self._metrics:
            mode = "eval" if self.control.should_evaluate else "train"
            self._metrics[mode]["completion_length"].append(completion_length.item())
            self._metrics[mode]["kl"].append(mean_kl.item())
        else:
            self._metrics["completion_length"].append(completion_length.item())
            self._metrics["kl"].append(mean_kl.item())
        return loss

    def _compute_loss(self, model, inputs):
        # Compute the per-token log probabilities for the model
        prompt_ids, prompt_mask = inputs["prompt_ids"], inputs["prompt_mask"]
        completion_ids, completion_mask = inputs["completion_ids"], inputs["completion_mask"]
        input_ids = torch.cat([prompt_ids, completion_ids], dim=1)
        attention_mask = torch.cat([prompt_mask, completion_mask], dim=1)
        logits_to_keep = completion_ids.size(1)  # we only need to compute the logits for the completion tokens

        per_token_logps = self._get_per_token_logps(model, input_ids, attention_mask, logits_to_keep)

        # Compute the KL divergence between the model and the reference model
        if self.beta != 0.0:
            ref_per_token_logps = inputs["ref_per_token_logps"]
            per_token_kl = (
                torch.exp(ref_per_token_logps - per_token_logps) - (ref_per_token_logps - per_token_logps) - 1
            )

        # Compute the loss
        advantages = inputs["advantages"]
        # When using num_iterations == 1 and steps_per_generation <= gradient_accumulation_steps
        # old_per_token_logps == per_token_logps, so we can skip it's computation
        # (see _generate_and_score_completions) and use per_token_logps.detach() instead.
        old_per_token_logps = (
            per_token_logps.detach() if inputs["old_per_token_logps"] is None else inputs["old_per_token_logps"]
        )
        coef_1 = torch.exp(per_token_logps - old_per_token_logps)
        coef_2 = torch.clamp(coef_1, 1 - self.epsilon_low, 1 + self.epsilon_high)

        # Two-sided clipping
        if self.args.delta is not None:
            coef_1 = torch.clamp(coef_1, max=self.args.delta)

        per_token_loss1 = coef_1 * advantages.unsqueeze(1)
        per_token_loss2 = coef_2 * advantages.unsqueeze(1)
        per_token_loss = -torch.min(per_token_loss1, per_token_loss2)
        if self.beta != 0.0:
            per_token_loss = per_token_loss + self.beta * per_token_kl

        if self.loss_type == "grpo":
            loss = ((per_token_loss * completion_mask).sum(-1) / completion_mask.sum(-1).clamp(min=1.0)).mean()
        elif self.loss_type == "bnpo":
            loss = (per_token_loss * completion_mask).sum() / completion_mask.sum().clamp(min=1.0)
        elif self.loss_type == "dr_grpo":
            loss = (per_token_loss * completion_mask).sum() / (per_token_loss.size(0) * self.max_completion_length)
        else:
            raise ValueError(f"Unknown loss type: {self.loss_type}")

        # Log the metrics
        mode = "train" if self.model.training else "eval"

        if self.beta != 0.0:
            mean_kl = (per_token_kl * completion_mask).sum() / completion_mask.sum()
            self._metrics[mode]["kl"].append(self.accelerator.gather(mean_kl).nanmean().item())

        # Compute the clipped probability ratios
        is_low_clipped = (coef_1 < 1 - self.epsilon_low) & (advantages.unsqueeze(1) < 0)
        is_high_clipped = (coef_1 > 1 + self.epsilon_high) & (advantages.unsqueeze(1) > 0)
        is_region_clipped = is_low_clipped | is_high_clipped

        low_clip = (is_low_clipped * completion_mask).sum() / completion_mask.sum()
        high_clip = (is_high_clipped * completion_mask).sum() / completion_mask.sum()
        clip_ratio = (is_region_clipped * completion_mask).sum() / completion_mask.sum()

        gathered_low_clip = self.accelerator.gather(low_clip)
        self._metrics[mode]["clip_ratio/low_mean"].append(gathered_low_clip.nanmean().item())
        self._metrics[mode]["clip_ratio/low_min"].append(nanmin(gathered_low_clip).item())
        gathered_high_clip = self.accelerator.gather(high_clip)
        self._metrics[mode]["clip_ratio/high_mean"].append(gathered_high_clip.nanmean().item())
        self._metrics[mode]["clip_ratio/high_max"].append(nanmax(gathered_high_clip).item())
        gathered_clip_ratio = self.accelerator.gather(clip_ratio)
        self._metrics[mode]["clip_ratio/region_mean"].append(gathered_clip_ratio.nanmean().item())
        return loss

    def prediction_step(self, model, inputs, prediction_loss_only, ignore_keys: Optional[list[str]] = None):
        inputs = self._prepare_inputs(inputs)
        with torch.no_grad():
            with self.compute_loss_context_manager():
                loss = self.compute_loss(model, inputs)
            loss = loss.mean().detach()
        return loss, None, None

    def log(self, logs: dict[str, float], start_time: Optional[float] = None) -> None:
        mode = "train" if self.model.training else "eval"
        metrics = {key: sum(val) / len(val) for key, val in self._metrics[mode].items()}  # average the metrics

        # This method can be called both in training and evaluation. When called in evaluation, the keys in `logs`
        # start with "eval_". We need to add the prefix "eval_" to the keys in `metrics` to match the format.
        if mode == "eval":
            metrics = {f"eval_{key}": val for key, val in metrics.items()}

        logs = {**logs, **metrics}
        super().log(logs, start_time)
        self._metrics[mode].clear()

        if self.accelerator.is_main_process and self.log_completions:
            if is_rich_available():
                print_prompt_completions_sample(
                    self._textual_logs["prompt"],
                    self._textual_logs["completion"],
                    self._textual_logs["rewards"],
                    self._textual_logs["advantages"],
                    self.state.global_step,
                    self.num_completions_to_print,
                )

            if self.args.report_to and "wandb" in self.args.report_to and wandb.run is not None:
                import pandas as pd

                table = {
                    "step": [str(self.state.global_step)] * len(self._textual_logs["prompt"]),
                    "prompt": self._textual_logs["prompt"],
                    "completion": self._textual_logs["completion"],
                    **self._textual_logs["rewards"],
                    "advantage": self._textual_logs["advantages"],
                }
                df = pd.DataFrame(table)
                if self.wandb_log_unique_prompts:
                    df = df.drop_duplicates(subset=["prompt"])
                wandb.log({"completions": wandb.Table(dataframe=df)})

    # Ensure the model card is saved along with the checkpoint
    def _save_checkpoint(self, model, trial):
        if self.args.hub_model_id is None:
            model_name = Path(self.args.output_dir).name
        else:
            model_name = self.args.hub_model_id.split("/")[-1]
        self.create_model_card(model_name=model_name)
        super()._save_checkpoint(model, trial)

    def create_model_card(
        self,
        model_name: Optional[str] = None,
        dataset_name: Optional[str] = None,
        tags: Union[str, list[str], None] = None,
    ):
        """
        Creates a draft of a model card using the information available to the `Trainer`.

        Args:
            model_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the model.
            dataset_name (`str` or `None`, *optional*, defaults to `None`):
                Name of the dataset used for training.
            tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                Tags to be associated with the model card.
        """
        if not self.is_world_process_zero():
            return

        if hasattr(self.model.config, "_name_or_path") and not os.path.isdir(self.model.config._name_or_path):
            base_model = self.model.config._name_or_path
        else:
            base_model = None

        # normalize `tags` to a mutable set
        if tags is None:
            tags = set()
        elif isinstance(tags, str):
            tags = {tags}
        else:
            tags = set(tags)

        if hasattr(self.model.config, "unsloth_version"):
            tags.add("unsloth")

        tags.update(self._tag_names)

        citation = textwrap.dedent(
            """\
            @article{zhihong2024deepseekmath,
                title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
                author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
                year         = 2024,
                eprint       = {arXiv:2402.03300},
            }
            """
        )

        model_card = generate_model_card(
            base_model=base_model,
            model_name=model_name,
            hub_model_id=self.hub_model_id,
            dataset_name=dataset_name,
            tags=tags,
            wandb_url=wandb.run.get_url() if is_wandb_available() and wandb.run is not None else None,
            comet_url=get_comet_experiment_url(),
            trainer_name="GRPO",
            trainer_citation=citation,
            paper_title="DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models",
            paper_id="2402.03300",
        )

        model_card.save(os.path.join(self.args.output_dir, "README.md"))
class UnslothGRPOTrainer(_UnslothGRPOTrainer):
    """
    
    Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the
    paper [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language
    Models](https://huggingface.co/papers/2402.03300).

    Example:

    ```python
    from datasets import load_dataset
    from trl import GRPOTrainer

    dataset = load_dataset("trl-lib/tldr", split="train")
    def reward_func(completions, **kwargs):
        # Dummy reward function that rewards completions with more unique letters.
        return [float(len(set(completion))) for completion in completions]
    trainer = GRPOTrainer(
        model="Qwen/Qwen2-0.5B-Instruct",
        reward_funcs=reward_func,
        train_dataset=dataset,
    )

    trainer.train()
    ```

    Args:
        model (`Union[str, PreTrainedModel]`):
            Model to be trained. Can be either:

            - A string, being the *model id* of a pretrained model hosted inside a model repo on huggingface.co, or a
              path to a *directory* containing model weights saved using
              [`~transformers.PreTrainedModel.save_pretrained`], e.g., `'./my_model_directory/'`. The model is loaded
              using [`~transformers.AutoModelForCausalLM.from_pretrained`] with the keyword arguments in
              `args.model_init_kwargs`.
            - A [`~transformers.PreTrainedModel`] object. Only causal language models are supported.
        reward_funcs (`Union[RewardFunc, list[RewardFunc]]`):
            Reward functions to be used for computing the rewards. To compute the rewards, we call all the reward
            functions with the prompts and completions and sum the rewards. Can be either:

            - A single reward function, such as:
                - A string: The *model ID* of a pretrained model hosted inside a model repo on huggingface.co, or a
                path to a *directory* containing model weights saved using
                [`~transformers.PreTrainedModel.save_pretrained`], e.g., `'./my_model_directory/'`. The model is loaded
                using [`~transformers.AutoModelForSequenceClassification.from_pretrained`] with `num_labels=1` and the
                keyword arguments in `args.model_init_kwargs`.
                - A [`~transformers.PreTrainedModel`] object: Only sequence classification models are supported.
                - A custom reward function: The function is provided with the prompts and the generated completions,
                  plus any additional columns in the dataset. It should return a list of rewards. Custom reward
                  functions can also return None when the reward is not applicable to those samples. This is useful for
                  multi-task training where different reward functions apply to different types of samples. When a
                  reward function returns None for a sample, that reward function is excluded from the reward
                  calculation for that sample. For more details, see [Using a custom reward
                  function](#using-a-custom-reward-function).
            - A list of reward functions, where each item can independently be any of the above types. Mixing different
            types within the list (e.g., a string model ID and a custom reward function) is allowed.
        args ([`GRPOConfig`], *optional*, defaults to `None`):
            Configuration for this trainer. If `None`, a default configuration is used.
        train_dataset ([`~datasets.Dataset`] or [`~datasets.IterableDataset`]):
            Dataset to use for training. It must include a column `"prompt"`. Any additional columns in the dataset is
            ignored. The format of the samples can be either:

            - [Standard](dataset_formats#standard): Each sample contains plain text.
            - [Conversational](dataset_formats#conversational): Each sample contains structured messages (e.g., role
              and content).
        eval_dataset ([`~datasets.Dataset`], [`~datasets.IterableDataset`] or `dict[str, Union[Dataset, IterableDataset]]`):
            Dataset to use for evaluation. It must meet the same requirements as `train_dataset`.
        processing_class ([`~transformers.PreTrainedTokenizerBase`], *optional*, defaults to `None`):
            Processing class used to process the data. The padding side must be set to "left". If `None`, the
            processing class is loaded from the model's name with [`~transformers.AutoTokenizer.from_pretrained`]. A
            padding token, `processing_class.pad_token`, must be set. If the processing class has not set a padding
            token, `processing_class.eos_token` will be used as the default.
        reward_processing_classes (`Union[PreTrainedTokenizerBase, list[PreTrainedTokenizerBase]]`, *optional*, defaults to `None`):
            Processing classes corresponding to the reward functions specified in `reward_funcs`. Can be either:

            - A single processing class: Used when `reward_funcs` contains only one reward function.
            - A list of processing classes: Must match the order and length of the reward functions in `reward_funcs`.
            If set to `None`, or if an element of the list corresponding to a [`~transformers.PreTrainedModel`] is
            `None`, the tokenizer for the model is automatically loaded using
            [`~transformers.AutoTokenizer.from_pretrained`]. For elements in `reward_funcs` that are custom reward
            functions (not [`~transformers.PreTrainedModel`]), the corresponding entries in `reward_processing_classes`
            are ignored.
        callbacks (list of [`~transformers.TrainerCallback`], *optional*, defaults to `None`):
            List of callbacks to customize the training loop. Will add those to the list of default callbacks detailed
            in [here](https://huggingface.co/docs/transformers/main_classes/callback).

            If you want to remove one of the default callbacks used, use the [`~transformers.Trainer.remove_callback`]
            method.
        optimizers (`tuple[torch.optim.Optimizer, torch.optim.lr_scheduler.LambdaLR]`, *optional*, defaults to `(None, None)`):
            A tuple containing the optimizer and the scheduler to use. Will default to an instance of [`AdamW`] on your
            model and a scheduler given by [`get_linear_schedule_with_warmup`] controlled by `args`.
        peft_config ([`~peft.PeftConfig`], *optional*, defaults to `None`):
            PEFT configuration used to wrap the model. If `None`, the model is not wrapped.
    
    """
    def __init__(
        self,
        model,
        reward_funcs,
        args = None,
        train_dataset = None,
        eval_dataset = None,
        processing_class = None,
        reward_processing_classes = None,
        callbacks = None,
        peft_config = None,
        **kwargs
    ):
        if args is None: args = UnslothGRPOConfig()
        use_bf16 = getattr(args, 'bf16', False)
        if type(use_bf16) is not bool: use_bf16 = False
        use_fp16 = getattr(args, 'fp16', False)
        if type(use_fp16) is not bool: use_fp16 = False
        force_float32 = False
        if os.environ.get('UNSLOTH_FORCE_FLOAT32', '0') == '1':
            print('Unsloth: Switching to float32 training since model cannot work with float16')
            force_float32 = True
        mixed_precision_dtype = os.environ.get('UNSLOTH_MIXED_PRECISION', 'float32')
        dtype = getattr(model.config, 'torch_dtype', None)
        if dtype is None: dtype = model.get_input_embeddings().dtype
        from unsloth_zoo.utils import _get_dtype
        dtype = _get_dtype(dtype)
        float16 = dtype == torch.float16
        if not force_float32 and (float16 and use_bf16): raise TypeError('Unsloth: Model is in float16 precision but you want to use bfloat16 precision. Set fp16 to `True` and bf16 to `False`')
        if not force_float32 and (not float16 and use_fp16): raise TypeError('Unsloth: Model is in bfloat16 precision but you want to use float16 precision. Set fp16 to `False` and bf16 to `True`')
        if force_float32:
            args.fp16 = False
            args.bf16 = False
            os.environ['ACCELERATE_MIXED_PRECISION'] = 'no'
        elif (not use_bf16 and not use_fp16) and mixed_precision_dtype == 'float32':
            args.fp16 = float16
            args.bf16 = not float16
            os.environ['ACCELERATE_MIXED_PRECISION'] = 'fp16' if float16 else 'bf16'
        if getattr(args, 'eval_dataset', None) is not None and getattr(args, 'eval_strategy', 'no') == 'no':
            args.eval_strategy = 'steps'
            if getattr(args, 'eval_steps', None) is None: args.eval_steps = 0.1
        ga_steps = getattr(args, 'gradient_accumulation_steps', None)
        if ga_steps is not None and ga_steps > 1:
            from transformers import __version__ as transformers_version
            if Version(transformers_version) <= Version('4.45.2'):
                print('**** Unsloth: Please use our fixed gradient_accumulation_steps by updating transformers, TRL and Unsloth!\n'
                      '`pip install --upgrade --no-cache-dir --force-reinstall --no-deps unsloth transformers trl unsloth_zoo`')
        if getattr(args, 'eval_strategy', 'no') != 'no':
            eval_bsz = getattr(args, 'per_device_eval_batch_size', 8)
            if eval_bsz == 8 and args.per_device_train_batch_size < eval_bsz: args.per_device_eval_batch_size = args.per_device_train_batch_size
            if getattr(args, 'eval_accumulation_steps', None) is None and ga_steps is not None: args.eval_accumulation_steps = ga_steps
        fp16_full_eval = getattr(args, 'fp16_full_eval', False)
        if type(fp16_full_eval) is not bool: fp16_full_eval = False
        bf16_full_eval = getattr(args, 'bf16_full_eval', False)
        if type(bf16_full_eval) is not bool: bf16_full_eval = False
        if args.fp16 and bf16_full_eval: args.bf16_full_eval = False; args.fp16_full_eval = True
        if args.bf16 and fp16_full_eval: args.bf16_full_eval = True; args.fp16_full_eval = False
        if force_float32:
            args.bf16_full_eval = False
            args.fp16_full_eval = False
        elif os.environ.get('UNSLOTH_MIXED_PRECISION', 'float32') == 'bfloat16':
            args.bf16_full_eval = True
            args.fp16_full_eval = False
        elif not bf16_full_eval and not fp16_full_eval:
            args.bf16_full_eval = args.bf16
            args.fp16_full_eval = args.fp16
        _output_logits = False
        if locals().get('compute_metrics', None) is not None: _output_logits = True
        if locals().get('preprocess_logits_for_metrics', None) is not None: _output_logits = True
        if _output_logits:
            os.environ['UNSLOTH_RETURN_LOGITS'] = '1'
        if 'max_seq_length' not in locals() and not hasattr(args, 'max_seq_length'):
            pass
        else:
            model_max_seq_length = getattr(model, 'max_seq_length', None)
            args_max_seq_length  = getattr(args,  'max_seq_length', None)
            if args_max_seq_length is None and model_max_seq_length is not None:
                max_seq_length = model.max_seq_length
                if hasattr(args, 'max_seq_length'): args.max_seq_length = max_seq_length
        if model is not None and hasattr(model, 'for_training'):
            model.for_training()
        if 'tokenizer' in locals() and hasattr(tokenizer, 'padding_side'): tokenizer.padding_side = 'right'
        if 'processing_class' in locals():
            if hasattr(processing_class, 'padding_side'): processing_class.padding_side = 'right'
            if hasattr(processing_class, 'tokenizer') and hasattr(processing_class.tokenizer, 'padding_side'): processing_class.tokenizer.padding_side = 'right'
        other_metrics = []
        if not isinstance(reward_funcs, list): _reward_funcs = [reward_funcs]
        else: _reward_funcs = reward_funcs
        for reward_func in _reward_funcs:
            try:
                reward_func_name = reward_func.__name__
                if True:
                    other_metrics.append(f'rewards/{reward_func_name}/mean')
                if True:
                    other_metrics.append(f'rewards/{reward_func_name}/std')
                if False:
                    other_metrics.append(f'rewards/{reward_func_name}')
            except: pass
        
        from unsloth_zoo.logging_utils import PatchRLStatistics
        PatchRLStatistics('grpo_trainer', other_metrics)
        
        super().__init__(
            model = model,
            reward_funcs = reward_funcs,
            args = args,
            train_dataset = train_dataset,
            eval_dataset = eval_dataset,
            processing_class = processing_class,
            reward_processing_classes = reward_processing_classes,
            callbacks = callbacks,
            peft_config = peft_config,**kwargs)
        if hasattr(self, 'neftune_hook_handle'):
            self.neftune_hook_handle.remove()
            if hasattr(self, 'neftune_hook_handle'): del self.neftune_hook_handle
        if getattr(args, 'neftune_noise_alpha', None) is not None:
            model.get_input_embeddings().neftune_noise_alpha = self.neftune_noise_alpha
        pass
        
pass