[trainer] Add Muon Optimizer (#7749)

Co-authored-by: hoshi-hiyouga <hiyouga@buaa.edu.cn>

examples/README.md

@@ -215,6 +215,12 @@ llamafactory-cli api examples/inference/llama3_lora_sft.yaml
 
 ### Extras
 
+#### Full-Parameter Fine-Tuning using Muon
+
+```bash
+llamafactory-cli train examples/extras/muon/qwen2_full_sft.yaml
+```
+
 #### Full-Parameter Fine-Tuning using GaLore
 
 ```bash

examples/README_zh.md

@@ -215,6 +215,12 @@ llamafactory-cli api examples/inference/llama3_lora_sft.yaml
 
 ### 杂项
 
+#### 使用 Muon 进行全参数训练
+
+```bash
+llamafactory-cli train examples/extras/muon/qwen2_full_sft.yaml
+```
+
 #### 使用 GaLore 进行全参数训练
 
 ```bash

examples/extras/muon/qwen2_full_sft.yaml

@@ -0,0 +1,43 @@
+### model
+model_name_or_path: Qwen/Qwen2-1.5B-Instruct
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+use_muon: true
+
+### dataset
+dataset: identity,alpaca_en_demo
+template: qwen
+cutoff_len: 2048
+max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: saves/qwen2-1_5b/full/sft
+logging_steps: 10
+save_steps: 500
+plot_loss: true
+overwrite_output_dir: true
+save_only_model: false
+report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 8
+learning_rate: 1.0e-5
+num_train_epochs: 3.0
+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