本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 使用 OpenAI 创建和管理开放权重模型的微调作业 APIs
<a name="fine-tuning-openai-job-create"></a>

兼容 OpenAI 的微调作业 APIs 允许您创建、监控和管理微调作业。本页重点介绍如何使用它们 APIs 进行钢筋微调。有关完整的 API 详细信息，请参阅[OpenAI微调文档](https://platform.openai.com/docs/api-reference/fine-tuning)。

## 创建微调作业
<a name="fine-tuning-openai-create-job"></a>

创建微调作业，开始根据给定数据集创建新模型的过程。如需完整的 API 详细信息，请参阅[OpenAI创建微调任务文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/methods/create)。

### 示例
<a name="fine-tuning-openai-create-job-examples"></a>

要使用 RFT 方法创建微调作业，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Create fine-tuning job with RFT method
job_response = client.fine_tuning.jobs.create(
    model=MODEL_ID,
    training_file=training_file_id,
    # Suffix field is not supported so commenting for now.
    # suffix="rft-example",  # Optional: suffix for fine-tuned model name
    extra_body={
        "method": {
            "type": "reinforcement", 
            "reinforcement": {
                "grader": {
                    "type": "lambda",
                    "lambda": {
                        "function": "arn:aws:lambda:us-west-2:123456789012:function:my-reward-function"  # Replace with your Lambda ARN
                    }
                },
                "hyperparameters": {
                    "n_epochs": 1,  # Number of training epochs
                    "batch_size": 4,  # Batch size
                    "learning_rate_multiplier": 1.0  # Learning rate multiplier
                }
            }
        }
    }
)

# Store job ID for next steps
job_id = job_response.id
print({job_id})
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/fine_tuning/jobs`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "training_file": "file-abc123",
    "model": "gpt-4o-mini",
    "method": {
      "type": "reinforcement",
      "reinforcement": {
        "grader": {
          "type": "lambda",
          "lambda": {
            "function": "arn:aws:lambda:us-west-2:123456789012:function:my-grader"
          }
        },
        "hyperparameters": {
          "n_epochs": 1,
          "batch_size": 4,
          "learning_rate_multiplier": 1.0
        }
      }
    }
  }'
```

------

## 列出微调事件
<a name="fine-tuning-openai-list-events"></a>

列出微调任务的事件。微调事件提供有关任务进度的详细信息，包括训练指标、检查点创建和错误消息。如需完整的 API 详细信息，请参阅[OpenAI列表微调事件文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/methods/list_events)。

### 示例
<a name="fine-tuning-openai-list-events-examples"></a>

要列出微调事件，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# List fine-tuning events
events = client.fine_tuning.jobs.list_events(
    fine_tuning_job_id="ftjob-abc123",
    limit=50
)

for event in events.data:
    print(f"[{event.created_at}] {event.level}: {event.message}")
    if event.data:
        print(f"  Metrics: {event.data}")
```

------
#### [ HTTP request ]

向以下地址发出 GET 请求`/v1/fine_tuning/jobs/{fine_tuning_job_id}/events`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123/events?limit=50
```

------

活动包括以下信息：
+ 培训开始和完成消息
+ 检查点创建通知
+ 每个步骤的训练指标（损失、准确性）
+ 任务失败时的错误消息

要对所有事件进行分页，请选择首选方法对应的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Paginate through all events
all_events = []
after = None

while True:
    events = client.fine_tuning.jobs.list_events(
        fine_tuning_job_id="ftjob-abc123",
        limit=100,
        after=after
    )
    
    all_events.extend(events.data)
    
    if not events.has_more:
        break
    
    after = events.data[-1].id
```

------
#### [ HTTP request ]

使用以下`after`参数发出多个 GET 请求：

```
# First request
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123/events?limit=100

# Subsequent requests with 'after' parameter
curl "https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123/events?limit=100&after=ft-event-abc123"
```

------

## 检索微调作业
<a name="fine-tuning-openai-retrieve-job"></a>

获取有关微调任务的详细信息。如需完整的 API 详细信息，请参阅[OpenAI检索微调任务文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/methods/retrieve)。

### 示例
<a name="fine-tuning-openai-retrieve-job-examples"></a>

要检索特定的工作详细信息，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Retrieve specific job details
job_details = client.fine_tuning.jobs.retrieve(job_id)

# Print raw response
print(json.dumps(job_details.model_dump(), indent=2))
```

------
#### [ HTTP request ]

向以下地址发出 GET 请求`/v1/fine_tuning/jobs/{fine_tuning_job_id}`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123 \
  -H "Authorization: Bearer $OPENAI_API_KEY"
```

------

## 列出微调任务
<a name="fine-tuning-openai-list-jobs"></a>

列出贵组织支持分页的微调任务。如需完整的 API 详细信息，请参阅[OpenAI列出微调任务文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/methods/list)。

### 示例
<a name="fine-tuning-openai-list-jobs-examples"></a>

要列出带有限制和分页的微调作业，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# List fine-tuning jobs with limit and pagination
response = client.fine_tuning.jobs.list(
    limit=20  # Maximum number of jobs to return
)

# Print raw response
print(json.dumps(response.model_dump(), indent=2))
```

------
#### [ HTTP request ]

向以下地址发出 GET 请求`/v1/fine_tuning/jobs`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs?limit=20 \
  -H "Authorization: Bearer $OPENAI_API_KEY"
```

------

## 取消微调作业
<a name="fine-tuning-openai-cancel-job"></a>

取消正在进行的微调任务。一旦取消，任务将无法恢复。如需完整的 API 详细信息，请参阅[OpenAI取消微调任务文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/methods/cancel)。

### 示例
<a name="fine-tuning-openai-cancel-job-examples"></a>

要取消微调作业，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Cancel fine-tuning job
cancel_response = client.fine_tuning.jobs.cancel("ftjob-abc123")

print(f"Job ID: {cancel_response.id}")
print(f"Status: {cancel_response.status}")  # Should be "cancelled"
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/fine_tuning/jobs/{fine_tuning_job_id}/cancel`：

```
curl -X POST https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123/cancel \
  -H "Authorization: Bearer $OPENAI_API_KEY"
```

------

## 列出微调检查点
<a name="fine-tuning-openai-list-checkpoints"></a>

列出微调作业的检查点。检查点是在微调期间创建的中间模型快照，可用于推断，以评估不同训练阶段的性能。有关更多信息，请参阅 [OpenAIList 微调检查点文档](https://developers.openai.com/api/reference/resources/fine_tuning/subresources/jobs/subresources/checkpoints/methods/list)。

### 示例
<a name="fine-tuning-openai-list-checkpoints-examples"></a>

要列出微调作业的检查点，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# List checkpoints for a fine-tuning job
checkpoints = client.fine_tuning.jobs.checkpoints.list(
    fine_tuning_job_id="ftjob-abc123",
    limit=10
)

for checkpoint in checkpoints.data:
    print(f"Checkpoint ID: {checkpoint.id}")
    print(f"Step: {checkpoint.step_number}")
    print(f"Model: {checkpoint.fine_tuned_model_checkpoint}")
    print(f"Metrics: {checkpoint.metrics}")
    print("---")
```

------
#### [ HTTP request ]

向以下地址发出 GET 请求`/v1/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/fine_tuning/jobs/ftjob-abc123/checkpoints?limit=10
```

------

每个检查点包括：
+ **检查点 ID**-检查点的唯一标识符
+ **步骤编号**-创建检查点的训练步骤
+ **模型检查点**-可用于推理的模型标识符
+ **指标**-此检查点的验证损失和准确性

要使用检查点模型进行推理，请选择首选方法的选项卡，然后按照以下步骤操作：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Test inference with a checkpoint
response = client.chat.completions.create(
    model=checkpoint.fine_tuned_model_checkpoint,
    messages=[{"role": "user", "content": "What is AI?"}],
    max_tokens=100
)

print(response.choices[0].message.content)
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/chat/completions`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ft:gpt-4o-mini:openai:custom:7p4lURel:ckpt-step-1000",
    "messages": [{"role": "user", "content": "What is AI?"}],
    "max_tokens": 100
  }'
```

------

## 使用经过微调的模型运行推理
<a name="fine-tuning-openai-inference"></a>

微调任务完成后，您可以使用经过微调的模型通过响应 API 或聊天完成 API 进行推理。有关 API 的完整详细信息，请参阅[使用生成响应 OpenAI APIs](bedrock-mantle.md)。

### 响应 API
<a name="fine-tuning-openai-responses-api"></a>

在经过微调的模型中使用 Responses API 生成单圈文本：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Get the fine-tuned model ID
job_details = client.fine_tuning.jobs.retrieve("ftjob-abc123")

if job_details.status == 'succeeded' and job_details.fine_tuned_model:
    fine_tuned_model = job_details.fine_tuned_model
    print(f"Using fine-tuned model: {fine_tuned_model}")
    
    # Run inference with Responses API
    response = client.completions.create(
        model=fine_tuned_model,
        prompt="What is the capital of France?",
        max_tokens=100,
        temperature=0.7
    )
    
    print(f"Response: {response.choices[0].text}")
else:
    print(f"Job status: {job_details.status}")
    print("Job must be in 'succeeded' status to run inference")
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/completions`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "ft:gpt-4o-mini:openai:custom-model:7p4lURel",
    "prompt": "What is the capital of France?",
    "max_tokens": 100,
    "temperature": 0.7
  }'
```

------

### 聊天完成 API
<a name="fine-tuning-openai-inference-examples"></a>

使用 Chat Completions API 与经过微调的模型进行对话互动：

------
#### [ OpenAI SDK (Python) ]

```
# Requires OPENAI_API_KEY and OPENAI_BASE_URL environment variables
from openai import OpenAI
client = OpenAI()

# Get the fine-tuned model ID
job_details = client.fine_tuning.jobs.retrieve("ftjob-abc123")

if job_details.status == 'succeeded' and job_details.fine_tuned_model:
    fine_tuned_model = job_details.fine_tuned_model
    print(f"Using fine-tuned model: {fine_tuned_model}")
    
    # Run inference
    inference_response = client.chat.completions.create(
        model=fine_tuned_model,
        messages=[
            {"role": "user", "content": "What is the capital of France?"}
        ],
        max_tokens=100
    )
    
    print(f"Response: {inference_response.choices[0].message.content}")
else:
    print(f"Job status: {job_details.status}")
    print("Job must be in 'succeeded' status to run inference")
```

------
#### [ HTTP request ]

向以下地址发出 POST 请求`/v1/chat/completions`：

```
curl https://bedrock-mantle.us-west-2.api.aws/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "ft:gpt-4o-mini:openai:custom-model:7p4lURel",
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "max_tokens": 100
  }'
```

------