View a markdown version of this page

使用 OpenAI APIs 建立和管理開放權重模型的微調任務 - Amazon Bedrock
建立微調任務列出微調事件擷取微調任務列出微調任務取消微調任務列出微調檢查點使用微調的模型執行推論

本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

使用 OpenAI APIs 建立和管理開放權重模型的微調任務

OpenAI 相容的微調任務 APIs 可讓您建立、監控和管理微調任務。此頁面會反白使用這些 APIs 進行強化微調。如需完整的 API 詳細資訊，請參閱OpenAI微調文件。

建立微調任務

建立微調任務，以開始從指定資料集建立新模型的程序。如需完整的 API 詳細資訊，請參閱OpenAI建立微調任務文件。

範例

若要使用 RFT 方法建立微調任務，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 POST 請求/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
        }
      }
    }
  }'

列出微調事件

列出微調任務的事件。微調事件提供任務進度的詳細資訊，包括訓練指標、檢查點建立和錯誤訊息。如需完整的 API 詳細資訊，請參閱OpenAI列出微調事件文件。

範例

若要列出微調事件，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 GET 請求/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

事件包括以下資訊：

  • 訓練已開始和已完成的訊息

  • 檢查點建立通知

  • 每個步驟的訓練指標 （遺失、準確性）

  • 任務失敗時的錯誤訊息

若要分頁所有事件，請選擇您偏好方法的標籤，然後遵循下列步驟：

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 after 參數提出多個 GET 請求：

# 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"

擷取微調任務

取得微調任務的詳細資訊。如需完整的 API 詳細資訊，請參閱OpenAI擷取微調任務文件。

範例

若要擷取特定任務詳細資訊，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 GET 請求/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"

列出微調任務

列出您組織具有分頁支援的微調任務。如需完整的 API 詳細資訊，請參閱OpenAI列出微調任務文件。

範例

若要列出具有限制和分頁的微調任務，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 GET 請求/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"

取消微調任務

取消進行中的微調任務。一旦取消，任務就無法繼續。如需完整的 API 詳細資訊，請參閱OpenAI取消微調任務文件。

範例

若要取消微調任務，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 POST 請求/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"

列出微調檢查點

列出微調任務的檢查點。檢查點是在微調期間建立的中繼模型快照，可用於推論，以評估不同訓練階段的效能。如需詳細資訊，請參閱OpenAI列出微調檢查點文件。

範例

若要列出微調任務的檢查點，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 GET 請求/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

每個檢查點包括：

  • 檢查點 ID – 檢查點的唯一識別符

  • 步驟編號 – 建立檢查點的訓練步驟

  • 模型檢查點 – 可用於推論的模型識別符

  • 指標 – 此檢查點的驗證遺失和準確性

若要使用檢查點模型進行推論，請選擇您偏好方法的索引標籤，然後遵循下列步驟：

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 提出 POST 請求/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
  }'

使用微調的模型執行推論

微調任務完成後，您可以透過回應 API 或聊天完成 API，使用微調模型進行推論。如需完整的 API 詳細資訊，請參閱 使用 OpenAI APIs產生回應。

回應 API

使用 Responses API 搭配您的微調模型進行單迴轉文字產生：

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 提出 POST 請求/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

使用聊天完成 API 與您的微調模型進行對話互動：

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 提出 POST 請求/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
  }'