fix trainer push to hub (#297)

Jintao-Huang · web-flow · commit fa5b3b167e03 · 2024-01-07T20:04:53.000+08:00
diff --git a/README.md b/README.md
@@ -128,7 +128,7 @@ Users can check the [documentation of SWIFT](docs/source/GetStarted/快速使用
   - Multi-Modal:
     - qwen-vl series: [qwen-vl](https://modelscope.cn/models/qwen/Qwen-VL/summary), [qwen-vl-chat](https://modelscope.cn/models/qwen/Qwen-VL-Chat/summary), [qwen-vl-chat-int4](https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary)
     - qwen-audio series: [qwen-audio](https://modelscope.cn/models/qwen/Qwen-Audio/summary), [qwen-audio-chat](https://modelscope.cn/models/qwen/Qwen-Audio-Chat/summary)
-    - Zhipu series:[cogagent-chat](https://www.modelscope.cn/models/ZhipuAI/cogagent-chat/summary),[cogagent-vqa](https://www.modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)
+    - Zhipu series: [cogagent-chat](https://www.modelscope.cn/models/ZhipuAI/cogagent-chat/summary), [cogagent-vqa](https://www.modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)
   - General:
     - qwen series: [qwen-1_8b-chat](https://modelscope.cn/models/qwen/Qwen-1_8B/summary), [qwen-1_8b-chat-int4](https://modelscope.cn/models/qwen/Qwen-1_8B-Chat-Int4/summary), [qwen-1_8b-chat-int8](https://modelscope.cn/models/qwen/Qwen-1_8B-Chat-Int8/summary), [qwen-7b](https://modelscope.cn/models/qwen/Qwen-7B/summary), [qwen-7b-chat](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), [qwen-7b-chat-int4](https://modelscope.cn/models/qwen/Qwen-7B-Chat-Int4/summary), [qwen-7b-chat-int8](https://modelscope.cn/models/qwen/Qwen-7B-Chat-Int8/summary), [qwen-14b](https://modelscope.cn/models/qwen/Qwen-14B/summary), [qwen-14b-chat](https://modelscope.cn/models/qwen/Qwen-14B-Chat/summary), [qwen-14b-chat-int4](https://modelscope.cn/models/qwen/Qwen-14B-Chat-Int4/summary), [qwen-14b-chat-int8](https://modelscope.cn/models/qwen/Qwen-14B-Chat-Int8/summary), [qwen-72b](https://modelscope.cn/models/qwen/Qwen-72B/summary), [qwen-72b-chat](https://modelscope.cn/models/qwen/Qwen-72B-Chat/summary), [qwen-72b-chat-int4](https://modelscope.cn/models/qwen/Qwen-72B-Chat-Int4/summary), [qwen-72b-chat-int8](https://modelscope.cn/models/qwen/Qwen-72B-Chat-Int8/summary)
     - chatglm series: [chatglm2-6b](https://modelscope.cn/models/ZhipuAI/chatglm2-6b/summary), [chatglm2-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm2-6b-32k/summary), [chatglm3-6b-base](https://modelscope.cn/models/ZhipuAI/chatglm3-6b-base/summary), [chatglm3-6b](https://modelscope.cn/models/ZhipuAI/chatglm3-6b/summary), [chatglm3-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm3-6b-32k/summary)
@@ -171,7 +171,7 @@ Users can check the [documentation of SWIFT](docs/source/GetStarted/快速使用
   - Custom Dataset
 - Supported Templates:
   - Text Generation: default-generation, default-generation-bos, chatglm-generation
-  - Chat: default, qwen, baichuan, chatglm2, chatglm3, llama, openbuddy, internlm, yi, xverse, ziya, skywork, bluelm, zephyr, sus, deepseek
+  - Chat: default, qwen, baichuan, chatglm2, chatglm3, llama, openbuddy, internlm, yi, xverse, ziya, skywork, bluelm, zephyr, sus, deepseek, codefuse-codellama, deepseek-coder, cogagent
 
 ## 🔥SCEdit
 
diff --git a/README_CN.md b/README_CN.md
@@ -126,7 +126,7 @@ SWIFT（Scalable lightWeight Infrastructure for Fine-Tuning）是一个可扩展
   - 多模态:
     - qwen-vl 系列: [qwen-vl](https://modelscope.cn/models/qwen/Qwen-VL/summary), [qwen-vl-chat](https://modelscope.cn/models/qwen/Qwen-VL-Chat/summary), [qwen-vl-chat-int4](https://modelscope.cn/models/qwen/Qwen-VL-Chat-Int4/summary)
     - qwen-audio 系列: [qwen-audio](https://modelscope.cn/models/qwen/Qwen-Audio/summary), [qwen-audio-chat](https://modelscope.cn/models/qwen/Qwen-Audio-Chat/summary)
-    - Zhipu多模态模型:[cogagent-chat](https://www.modelscope.cn/models/ZhipuAI/cogagent-chat/summary),[cogagent-vqa](https://www.modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)
+    - Zhipu多模态模型: [cogagent-chat](https://www.modelscope.cn/models/ZhipuAI/cogagent-chat/summary), [cogagent-vqa](https://www.modelscope.cn/models/ZhipuAI/cogagent-vqa/summary)
   - 通用:
     - qwen 系列: [qwen-1_8b-chat](https://modelscope.cn/models/qwen/Qwen-1_8B/summary), [qwen-1_8b-chat-int4](https://modelscope.cn/models/qwen/Qwen-1_8B-Chat-Int4/summary), [qwen-1_8b-chat-int8](https://modelscope.cn/models/qwen/Qwen-1_8B-Chat-Int8/summary), [qwen-7b](https://modelscope.cn/models/qwen/Qwen-7B/summary), [qwen-7b-chat](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), [qwen-7b-chat-int4](https://modelscope.cn/models/qwen/Qwen-7B-Chat-Int4/summary), [qwen-7b-chat-int8](https://modelscope.cn/models/qwen/Qwen-7B-Chat-Int8/summary), [qwen-14b](https://modelscope.cn/models/qwen/Qwen-14B/summary), [qwen-14b-chat](https://modelscope.cn/models/qwen/Qwen-14B-Chat/summary), [qwen-14b-chat-int4](https://modelscope.cn/models/qwen/Qwen-14B-Chat-Int4/summary), [qwen-14b-chat-int8](https://modelscope.cn/models/qwen/Qwen-14B-Chat-Int8/summary), [qwen-72b](https://modelscope.cn/models/qwen/Qwen-72B/summary), [qwen-72b-chat](https://modelscope.cn/models/qwen/Qwen-72B-Chat/summary), [qwen-72b-chat-int4](https://modelscope.cn/models/qwen/Qwen-72B-Chat-Int4/summary), [qwen-72b-chat-int8](https://modelscope.cn/models/qwen/Qwen-72B-Chat-Int8/summary)
     - chatglm 系列: [chatglm2-6b](https://modelscope.cn/models/ZhipuAI/chatglm2-6b/summary), [chatglm2-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm2-6b-32k/summary), [chatglm3-6b-base](https://modelscope.cn/models/ZhipuAI/chatglm3-6b-base/summary), [chatglm3-6b](https://modelscope.cn/models/ZhipuAI/chatglm3-6b/summary), [chatglm3-6b-32k](https://modelscope.cn/models/ZhipuAI/chatglm3-6b-32k/summary)
@@ -169,7 +169,7 @@ SWIFT（Scalable lightWeight Infrastructure for Fine-Tuning）是一个可扩展
   - 自定义数据集
 - 支持的对话模板:
   - 文本生成: default-generation, default-generation-bos, chatglm-generation
-  - 对话: default, qwen, baichuan, chatglm2, chatglm3, llama, openbuddy, internlm, yi, xverse, ziya, skywork, bluelm, zephyr, sus, deepseek
+  - 对话: default, qwen, baichuan, chatglm2, chatglm3, llama, openbuddy, internlm, yi, xverse, ziya, skywork, bluelm, zephyr, sus, deepseek, codefuse-codellama, deepseek-coder, cogagent
 
 ## 🔥SCEdit
 
diff --git a/docs/source/LLM/命令行参数.md b/docs/source/LLM/命令行参数.md
@@ -62,7 +62,7 @@
 - `--warmup_ratio`: warmup占用总的训练steps的比例, 默认为`0.05`.
 - `--eval_steps`: 每训练多少steps进行评估, 默认为`50`.
 - `--save_steps`: 每训练多少个steps进行保存, 默认为`None`, 即设置为`eval_steps`.
-- `--only_save_model`: 是否只保存模型参数, 而不存储断点续训所需的中间状态, 默认为`None`, 即如果`sft_type`为'lora'并且不使用deepspeed(`deepspeed_config_path`为None), 设置为False, 否则设置为True(e.g. 使用了全参数微调或者使用了deepspeed).
+- `--save_only_model`: 是否只保存模型参数, 而不存储断点续训所需的中间状态, 默认为`None`, 即如果`sft_type`为'lora'并且不使用deepspeed(`deepspeed_config_path`为None), 设置为False, 否则设置为True(e.g. 使用了全参数微调或者使用了deepspeed).
 - `--save_total_limit`: 保存的checkpoint的数量, 默认为`2`, 即保存best和last的checkpoint. 如果设置为-1, 则保存所有的checkpoint.
 - `--logging_steps`: 每训练多少步打印训练信息(e.g. loss, learning_rate等), 默认为`5`.
 - `--dataloader_num_workers`: 默认值为`1`.
diff --git a/examples/pytorch/llm/scripts/baichuan2_13b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_13b_chat/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan2_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_13b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan2_13b_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_13b_chat_int4/qlora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan2_7b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_7b_chat/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan2_7b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_7b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan2_7b_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan2_7b_chat_int4/qlora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/baichuan_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/baichuan_13b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/chatglm2_6b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/chatglm2_6b/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/chatglm3_6b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/chatglm3_6b/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/chatglm3_6b_base/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/chatglm3_6b_base/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/codegeex2_6b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/codegeex2_6b/lora_ddp_ds/sft.sh
@@ -40,4 +40,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/custom/tigerbot_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/custom/tigerbot_13b_chat/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/custom/tigerbot_7b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/custom/tigerbot_7b/lora_ddp_ds/sft.sh
@@ -40,4 +40,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/llama2_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/llama2_13b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/llama2_70b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/llama2_70b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/mistral_7b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/mistral_7b_chat/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/mixtral_7b_moe/lora/sft.sh b/examples/pytorch/llm/scripts/mixtral_7b_moe/lora/sft.sh
@@ -31,4 +31,4 @@ python llm_sft.py \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/mixtral_7b_moe_chat/lora/sft.sh b/examples/pytorch/llm/scripts/mixtral_7b_moe_chat/lora/sft.sh
@@ -31,4 +31,4 @@ python llm_sft.py \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/openbuddy_llama2_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/openbuddy_llama2_13b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/openbuddy_llama2_70b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/openbuddy_llama2_70b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/openbuddy_mistral_7b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/openbuddy_mistral_7b_chat/lora_ddp_ds/sft.sh
@@ -41,4 +41,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/phi2_3b/lora/sft.sh b/examples/pytorch/llm/scripts/phi2_3b/lora/sft.sh
@@ -12,7 +12,7 @@ swift sft \
     --max_length 2048 \
     --learning_rate 1e-4 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --lora_target_modules ALL \
     --dataset codefuse-python-en \
     --gradient_checkpointing false \
diff --git a/examples/pytorch/llm/scripts/polylm_13b/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/polylm_13b/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b/qlora_ddp_ds/sft.sh
@@ -44,4 +44,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b_chat/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b_chat/qlora_ddp_ds/sft.sh
@@ -45,4 +45,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b_chat_int4/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_14b_chat_int8/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_14b_chat_int8/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_1_8b_chat/full/sft.sh b/examples/pytorch/llm/scripts/qwen_1_8b_chat/full/sft.sh
@@ -23,7 +23,7 @@ python llm_sft.py \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model true \
+    --save_only_model true \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn false \
diff --git a/examples/pytorch/llm/scripts/qwen_1_8b_chat/full_ddp/sft.sh b/examples/pytorch/llm/scripts/qwen_1_8b_chat/full_ddp/sft.sh
@@ -30,7 +30,7 @@ torchrun \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model true \
+    --save_only_model true \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn false \
diff --git a/examples/pytorch/llm/scripts/qwen_72b_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_72b_chat_int4/qlora_ddp_ds/sft.sh
@@ -43,5 +43,5 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
     --tuner_backend peft \
diff --git a/examples/pytorch/llm/scripts/qwen_72b_chat_int8/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_72b_chat_int8/qlora_ddp_ds/sft.sh
@@ -44,4 +44,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_7b/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/full/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/full/sft.sh
@@ -11,6 +11,6 @@ swift sft \
     --max_length 4096 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset codefuse-evol-instruction-zh \
     --preprocess_num_proc 4 \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/full_freeze_ddp/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/full_freeze_ddp/sft.sh
@@ -12,7 +12,7 @@ swift sft \
     --max_length 4096 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset codefuse-evol-instruction-zh \
     --freeze_parameters 0.25 \
     --additional_trainable_parameters transformer.wte \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/full_mp/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/full_mp/sft.sh
@@ -23,7 +23,7 @@ python llm_sft.py \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model true \
+    --save_only_model true \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/full_mp_ddp/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/full_mp_ddp/sft.sh
@@ -28,7 +28,7 @@ torchrun \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model true \
+    --save_only_model true \
     --save_total_limit 2 \
     --logging_steps 10 \
     --use_flash_attn true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat/qlora_ddp_ds/sft.sh
@@ -45,4 +45,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat_int4/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_7b_chat_int8/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_7b_chat_int8/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_audio_chat/full_mp/sft.sh b/examples/pytorch/llm/scripts/qwen_audio_chat/full_mp/sft.sh
@@ -11,6 +11,6 @@ swift sft \
     --max_length 2048 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset aishell1-mini-zh \
     --lazy_tokenize true \
diff --git a/examples/pytorch/llm/scripts/qwen_audio_chat/full_mp_ddp/sft.sh b/examples/pytorch/llm/scripts/qwen_audio_chat/full_mp_ddp/sft.sh
@@ -12,6 +12,6 @@ swift sft \
     --max_length 2048 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset aishell1-mini-zh \
     --lazy_tokenize true \
diff --git a/examples/pytorch/llm/scripts/qwen_audio_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_audio_chat/lora_ddp_ds/sft.sh
@@ -41,5 +41,5 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
     --lazy_tokenize true \
diff --git a/examples/pytorch/llm/scripts/qwen_vl/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_vl/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_vl_chat/full_mp/sft.sh b/examples/pytorch/llm/scripts/qwen_vl_chat/full_mp/sft.sh
@@ -11,5 +11,5 @@ swift sft \
     --max_length 2048 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset coco-mini-en \
diff --git a/examples/pytorch/llm/scripts/qwen_vl_chat/full_mp_ddp/sft.sh b/examples/pytorch/llm/scripts/qwen_vl_chat/full_mp_ddp/sft.sh
@@ -12,5 +12,5 @@ swift sft \
     --max_length 2048 \
     --learning_rate 2e-5 \
     --use_flash_attn true \
-    --only_save_model true \
+    --save_only_model true \
     --dataset coco-mini-en \
diff --git a/examples/pytorch/llm/scripts/qwen_vl_chat/lora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_vl_chat/lora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/qwen_vl_chat_int4/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/qwen_vl_chat_int4/qlora_ddp_ds/sft.sh
@@ -42,4 +42,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/examples/pytorch/llm/scripts/seqgpt_560m/full/sft.sh b/examples/pytorch/llm/scripts/seqgpt_560m/full/sft.sh
@@ -23,7 +23,7 @@ python llm_sft.py \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model false \
+    --save_only_model false \
     --save_total_limit 2 \
     --logging_steps 10 \
     --push_to_hub false \
diff --git a/examples/pytorch/llm/scripts/seqgpt_560m/full_ddp/sft.sh b/examples/pytorch/llm/scripts/seqgpt_560m/full_ddp/sft.sh
@@ -29,7 +29,7 @@ torchrun \
     --warmup_ratio 0.03 \
     --eval_steps 100 \
     --save_steps 100 \
-    --only_save_model false \
+    --save_only_model false \
     --save_total_limit 2 \
     --logging_steps 10 \
     --push_to_hub false \
diff --git a/examples/pytorch/llm/scripts/ziya2_13b_chat/qlora_ddp_ds/sft.sh b/examples/pytorch/llm/scripts/ziya2_13b_chat/qlora_ddp_ds/sft.sh
@@ -43,4 +43,4 @@ torchrun \
     --hub_private_repo true \
     --hub_token 'your-sdk-token' \
     --deepspeed_config_path 'ds_config/zero2.json' \
-    --only_save_model true \
+    --save_only_model true \
diff --git a/swift/llm/dpo.py b/swift/llm/dpo.py
diff --git a/swift/llm/sft.py b/swift/llm/sft.py
diff --git a/swift/llm/utils/argument.py b/swift/llm/utils/argument.py
diff --git a/swift/trainers/arguments.py b/swift/trainers/arguments.py
diff --git a/swift/trainers/mixin.py b/swift/trainers/mixin.py
diff --git a/swift/utils/torch_utils.py b/swift/utils/torch_utils.py
diff --git a/tests/trainers/test_trainer.py b/tests/trainers/test_trainer.py
