[example] add bash usage (#7794)

examples/README.md

@@ -24,7 +24,13 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
 Advanced usage:
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml learning_rate=1e-5 logging_steps=1
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
+    learning_rate=1e-5 \
+    logging_steps=1
+```
+
+```bash
+bash examples/train_lora/llama3_lora_sft.sh
 ```
 
 ## Examples
@@ -215,12 +221,6 @@ 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
@@ -245,6 +245,12 @@ llamafactory-cli train examples/extras/badam/llama3_full_sft.yaml
 llamafactory-cli train examples/extras/adam_mini/qwen2_full_sft.yaml
 ```
 
+#### Full-Parameter Fine-Tuning using Muon
+
+```bash
+llamafactory-cli train examples/extras/muon/qwen2_full_sft.yaml
+```
+
 #### LoRA+ Fine-Tuning
 
 ```bash

examples/README_zh.md

@@ -24,7 +24,13 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
 高级用法：
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml learning_rate=1e-5 logging_steps=1
+CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml \
+    learning_rate=1e-5 \
+    logging_steps=1
+```
+
+```bash
+bash examples/train_lora/llama3_lora_sft.sh
 ```
 
 ## 示例
@@ -215,12 +221,6 @@ 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
@@ -245,6 +245,12 @@ llamafactory-cli train examples/extras/badam/llama3_full_sft.yaml
 llamafactory-cli train examples/extras/adam_mini/qwen2_full_sft.yaml
 ```
 
+#### 使用 Muon 进行全参数训练
+
+```bash
+llamafactory-cli train examples/extras/muon/qwen2_full_sft.yaml
+```
+
 #### LoRA+ 微调
 
 ```bash

examples/train_lora/llama3_lora_sft.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -x
+
+MODEL_PATH=meta-llama/Meta-Llama-3-8B-Instruct
+
+llamafactory-cli train \
+    --model_name_or_path ${MODEL_PATH} \
+    --trust_remote_code \
+    --stage sft \
+    --do_train \
+    --finetuning_type lora \
+    --lora_rank 8 \
+    --lora_target all \
+    --dataset identity,alpaca_en_demo \
+    --template llama3 \
+    --cutoff_len 2048 \
+    --max_samples 1000 \
+    --overwrite_cache \
+    --preprocessing_num_workers 16 \
+    --dataloader_num_workers 4 \
+    --output_dir saves/llama3-8b/lora/sft \
+    --logging_steps 10 \
+    --save_steps 500 \
+    --plot_loss \
+    --overwrite_output_dir \
+    --save_only_model false \
+    --report_to none \
+    --per_device_train_batch_size 1 \
+    --gradient_accumulation_steps 8 \
+    --learning_rate 1e-4 \
+    --num_train_epochs 3.0 \
+    --lr_scheduler_type cosine \
+    --warmup_ratio 0.1 \
+    --bf16 \
+    --ddp_timeout 180000000