mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-22 13:42:51 +08:00
40 lines
1.4 KiB
Python
40 lines
1.4 KiB
Python
from types import MethodType
|
|
from typing import TYPE_CHECKING, Optional
|
|
|
|
import torch
|
|
from transformers import Seq2SeqTrainer
|
|
|
|
from ...extras.logging import get_logger
|
|
from ..utils import create_custom_optimzer, create_custom_scheduler
|
|
|
|
|
|
if TYPE_CHECKING:
|
|
from ...hparams import FinetuningArguments
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
class CustomSeq2SeqTrainer(Seq2SeqTrainer):
|
|
r"""
|
|
Inherits Seq2SeqTrainer to compute generative metrics such as BLEU and ROUGE.
|
|
"""
|
|
|
|
def __init__(self, finetuning_args: "FinetuningArguments", **kwargs) -> None:
|
|
super().__init__(**kwargs)
|
|
self.finetuning_args = finetuning_args
|
|
if finetuning_args.use_badam:
|
|
from badam import clip_grad_norm_for_sparse_tensor
|
|
|
|
self.accelerator.clip_grad_norm_ = MethodType(clip_grad_norm_for_sparse_tensor, self.accelerator)
|
|
|
|
def create_optimizer(self) -> "torch.optim.Optimizer":
|
|
if self.optimizer is None:
|
|
self.optimizer = create_custom_optimzer(self.model, self.args, self.finetuning_args)
|
|
return super().create_optimizer()
|
|
|
|
def create_scheduler(
|
|
self, num_training_steps: int, optimizer: Optional["torch.optim.Optimizer"] = None
|
|
) -> "torch.optim.lr_scheduler.LRScheduler":
|
|
create_custom_scheduler(self.args, num_training_steps, optimizer)
|
|
return super().create_scheduler(num_training_steps, optimizer)
|