Fine-tune with the API or CLI

SFT training set

The SFT training set uses the ChatML (Chat Markup Language) format, which supports multi-turn conversation and various role settings.

OpenAI's name and weight parameters are not supported. All assistant outputs are trained.

# A single line of training data (JSON format) has the following structure:
{"messages": [
  {"role": "system", "content": "System input 1"}, 
  {"role": "user", "content": "User input 1"}, 
  {"role": "assistant", "content": "Expected model output 1"}, 
  {"role": "user", "content": "User input 2"}, 
  {"role": "assistant", "content": "Expected model output 2"}
  ...
]}

For an explanation of the system, user, and assistant roles, see Overview. For dataset examples, see SFT-ChatML-format-example.jsonl and SFT-ChatML-format-example.xlsx (XLS and XLSX formats support only single-turn conversations).

All assistant rows in a single training data entry support the "loss_weight" parameter, which is used to set the relative importance of that row during training. (The valid range is 0.0 to 1.0, and a larger value indicates higher importance.)

This is an invitation-only parameter. To use it, please contact your account manager.

 {"role": "assistant", "content": "Expected model output 1", "loss_weight": 1.0}, 
 {"role": "assistant", "content": "Expected model output 2", "loss_weight": 0.5}

SFT thinking model

The training data supports multi-turn conversation and various role settings, but only the final assistant output is used for training. A single line of training data has the following structure:

The \n characters before and after the <think> tag must be preserved.

# A single line of training data (JSON format) has the following structure:
{"messages": [
  {"role": "system", "content": "System input 1"}, 
  {"role": "user", "content": "User input 1"}, 
  {"role": "assistant", "content": "Model output 1"}, -- Intermediate assistant outputs should not include <think> tags.
   ...
  {"role": "user", "content": "User input 2"}, 
  {"role": "assistant", "content": "<think>\nExpected thinking content 2\n</think>\n\nExpected output 2"} -- Thinking content can only be included in the last assistant output.
]}

For an explanation of the system, user, and assistant roles, see Overview. For a dataset example, see SFT-deep-thinking-content-example.jsonl.

You can also configure the model in the training samples to not output the <think> tag. If you use this output method, we do not recommend enabling the thinking mode for calls after the model is trained.

{"role": "assistant", "content": "Expected model output 2"}  -- Instructs the model not to enable thinking mode.

The last assistant line of a single training data entry supports the "loss_weight" parameter to set the relative importance of that entry during training. (The valid range is 0.0 ~ 1.0, where a larger value indicates higher importance.)

This is an invitation-only parameter. To use it, please contact your account manager.

 {"role": "assistant", "content": "<think>\nExpected thinking content 2\n</think>\n\nExpected output 2", "loss_weight": 1.0}

SFT visual understanding (Qwen-VL)

The name and weight parameters of OpenAI are not supported, and all assistant outputs are trained.

For an explanation of the system, user, and assistant roles, see Overview. The following is an example of training data in the ChatML format:

To pass a system message, the corresponding content must be in the array format [{"text":"..."}], and not the string format "content":"string".

# A single line of training data (JSON format) has the following structure:
{"messages": [
  {"role": "system", "content": [{"text": "System input"}]},
  {"role": "user", "content": [{"text": "User input 1"}, {"image": "image_filename_1.jpg", "resized_width": 200, "resized_height": 200}]},
  {"role": "assistant", "content": [{"text": "Expected model output 1"}]},
  {"role": "user", "content": [{"text": "User input 2"}, {"video": "video_filename_1.mp4", "fps": 3.0, "resized_width": 200, "resized_height": 200, "video_start": 0.0, "video_end": 3.0}]},
  {"role": "assistant", "content": [{"text": "Expected model output 2"}]},
  {"role": "user", "content": [{"text": "User input 2"}, {"video": ["0.jpg", "1.jpg", "2.jpg", "3.jpg"], "sample_fps": 5.0, "resized_width": 200, "resized_height": 200}]},
  {"role": "assistant", "content": [{"text": "Expected model output 2"}]},
  ...
]}

DPO dataset

The DPO dataset uses the ChatML format. A single training example has the following structure:

For an explanation of the system, user, and assistant roles, see Overview. For a dataset example, see DPO-ChatML-format-example.jsonl.

# A single line of training data (JSON format) has the following structure:
{"messages": [
  {"role": "system", "content": "System input"},
  {"role": "user", "content": "User input 1"},
  {"role": "assistant", "content": "Model output 1"},
  {"role": "user", "content": "User input 2"},
  {"role": "assistant", "content": "Model output 2"},
  {"role": "user", "content": "User input 3"}
 ],
 "chosen":
   {"role": "assistant", "content": "Preferred model output 3"},
 "rejected":
   {"role": "assistant", "content": "Rejected model output 3"}}

The model takes all content within messages as input, and DPO trains the model on the positive and negative feedback for User Input 3.

Wrap content for in-depth thoughts in the <think> tag:

{"role": "assistant", "content": "<think>Expected model thinking content</think>Expected model output"}

The "chosen" module of a single training data entry supports the "loss_weight" parameter, which is used to set the relative importance of that entry during training. (The valid range is 0.0 to 1.0, where a larger value indicates higher importance.)

This is an invitation-only parameter. To use it, please contact your account manager.

 "chosen":
   {"role": "assistant", "content": "Preferred model output 3", "loss_weight": 1.0},

CPT training set

The CPT training set uses the plain text format. A single training example has the following structure:

{"text":"Text content"}

For a dataset example, see CPT-text-generation-training-set-example.jsonl.

DashScope API

For Windows CMD, replace ${DASHSCOPE_API_KEY} with %DASHSCOPE_API_KEY%. For PowerShell, replace it with $env:DASHSCOPE_API_KEY.

curl --request POST \
'https://dashscope.aliyuncs.com/api/v1/files' \
--header 'Authorization: Bearer '${DASHSCOPE_API_KEY} \
--form 'files=@"/path/to/your/file.jsonl"' \
--form 'purpose="fine-tune"' \
--form 'descriptions="a sample fine-tune data file for qwen"'

Sample response:

{
  "request_id":"xx",
  "data":{
    "uploaded_files":[{
      "file_id":"976bd01a-f30b-4414-86fd-50c54486e3ef",
      "name":"qwen-fine-tune-sample.jsonl"}],
  　"failed_uploads":[]}
 }

HTTP

curl 'https://dashscope.aliyuncs.com/api/v1/fine-tunes/<job_id>' \
--header 'Authorization: Bearer '${DASHSCOPE_API_KEY} \
--header 'Content-Type: application/json'

{
    "request_id": "d100cddb-ac85-4c82-bd5c-9b5421c5e94d",
    "output":
    {
        "job_id": "ft-202511272033-8ae7",
        "job_name": "ft-202511272033-8ae7",
        "status": "RUNNING",
        "finetuned_output": "qwen3-8b-ft-202511272033-8ae7",
        "model": "qwen3-8b",
        "base_model": "qwen3-8b",
        "training_file_ids":
        [
            "9e9ffdfa-c3bf-436e-9613-6f053c66aa6e"
        ],
        "validation_file_ids":
        [],
        "hyper_parameters":
        {
            "n_epochs": 3,
            "batch_size": 16,
            "max_length": 8192,
            "learning_rate": "1.6e-5",
            "lr_scheduler_type": "linear",
            "split": 0.9,
            "warmup_ratio": 0.05,
            "eval_steps": 50,
            "data_augmentation": true,
            "augmentation_ratio": "0.1,0.05,0.15",
            "augmentation_types": "dialogue_CN,general_purpose_CN,NLP",
            "save_strategy": "epoch",
            "save_total_limit": 10
        },
        "training_type": "sft",
        "create_time": "2025-11-27 20:33:15",
        "workspace_id": "llm-8v53etv3hwb8orx1",
        "user_identity": "1654290265984853",
        "modifier": "1654290265984853",
        "creator": "1654290265984853",
        "group": "llm",
        "max_output_cnt": 10
    }
}

HTTP

curl 'https://dashscope.aliyuncs.com/api/v1/fine-tunes/<job_id>/logs?offset=0&line=1000' \
--header 'Authorization: Bearer '${DASHSCOPE_API_KEY} \
--header 'Content-Type: application/json' 

Use the offset and line parameters to retrieve a specific range of log lines. The offset parameter sets the starting position for the log output, and the line parameter sets the maximum number of lines to return.

Sample response:

{
    "request_id":"1100d073-4673-47df-aed8-c35b3108e968",
    "output":{
        "total":57,
        "logs":[
            "{Log entry 1}",
            "{Log entry 2}",
            ...
            ...
            ...
        ]
    }
}