fix src/llamafactory/train/callbacks.py

[yzoaim]

What does this PR do?

Fixes # (issue)

Before submitting

• Did you read the contributor guideline?
• Did you write any new necessary tests?

在 examples/train_lora/llama3_lora_reward.yaml 中添加了一行配置使用deepspeed， 训练完成后保存模型不成功，报错TypeError:str.replace()takes no keyword arguments。配置如下

### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct

### method
stage: rm
do_train: true
finetuning_type: lora
lora_target: all
deepspeed: examples/deepspeed/ds_z3_config.json

### dataset
dataset: dpo_en_demo
template: llama3
cutoff_len: 1024
max_samples: 50
overwrite_cache: true

### output
output_dir: saves/llama3-8b/lora/rewardfix
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 1
gradient_accumulation_steps: 8
learning_rate: 1.0e-4
num_train_epochs: 1.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.1
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500

定位到src/llamafactory/train/callbacks.py的方法fix_valuehead_checkpoint中，修改后可以正确保存模型