新版本 2.0 上的 SFT

Amazon Nova Lite 2.0 為監督式微調提供了增強功能，包括進階推理模式、改善多模態理解和延伸內容處理。在 Nova 2.0 上的 SFT 可讓您將這些強大的功能適應您的特定使用案例，同時在複雜的任務上維持模型的卓越效能。

SFT on Nova 2.0 的主要功能包括：

run:
  name: my-full-rank-sft-run
  model_type: amazon.nova-2-lite-v1:0:256k
  model_name_or_path: nova-lite-2/prod
  data_s3_path: s3://my-bucket-name/train.jsonl  #  only and not compatible with SageMaker Training Jobs
  replicas: 4                                     # Number of compute instances for training, allowed values are 4, 8, 16, 32
  output_s3_path: s3://my-bucket-name/outputs/    # Output artifact path (HyperPod job-specific; not compatible with standard SageMaker Training Jobs)
  mlflow_tracking_uri: ""                         # Required for MLFlow
  mlflow_experiment_name: "my-full-rank-sft-experiment"  # Optional for MLFlow. Note: leave this field non-empty
  mlflow_run_name: "my-full-rank-sft-run"         # Optional for MLFlow. Note: leave this field non-empty

training_config:
  max_steps: 100                    # Maximum training steps. Minimal is 4.
  save_steps: ${oc.select:training_config.max_steps}  # How many training steps the checkpoint will be saved
  save_top_k: 5                     # Keep top K best checkpoints. Note supported only for  jobs. Minimal is 1.
  max_length: 32768                 # Sequence length (options: 8192, 16384, 32768 [default], 65536)
  global_batch_size: 32             # Global batch size (options: 32, 64, 128)
  reasoning_enabled: true           # If data has reasoningContent, set to true; otherwise False

  lr_scheduler:
    warmup_steps: 15                # Learning rate warmup steps. Recommend 15% of max_steps
    min_lr: 1e-6                    # Minimum learning rate, must be between 0.0 and 1.0

  optim_config:                     # Optimizer settings
    lr: 1e-5                        # Learning rate, must be between 0.0 and 1.0
    weight_decay: 0.0               # L2 regularization strength, must be between 0.0 and 1.0
    adam_beta1: 0.9                  # Exponential decay rate for first-moment estimates
    adam_beta2: 0.95                 # Exponential decay rate for second-moment estimates

  peft:                             # Parameter-efficient fine-tuning (LoRA)
    peft_scheme: "null"             # Disable LoRA for PEFT

選擇合理模式 （僅限 Nova 2.0)

Amazon Nova 2.0 支援增強分析功能的推理模式：

工具呼叫資料格式

SFT 支援訓練模型以使用工具 （函數呼叫）。以下是工具呼叫的範例輸入格式：

範例輸入：

{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are an expert in composing function calls."
    }
  ],
  "toolConfig": {
    "tools": [
      {
        "toolSpec": {
          "name": "getItemCost",
          "description": "Retrieve the cost of an item from the catalog",
          "inputSchema": {
            "json": {
              "type": "object",
              "properties": {
                "item_name": {
                  "type": "string",
                  "description": "The name of the item to retrieve cost for"
                },
                "item_id": {
                  "type": "string",
                  "description": "The ASIN of item to retrieve cost for"
                }
              },
              "required": [
                "item_id"
              ]
            }
          }
        }
      },
      {
        "toolSpec": {
          "name": "getItemAvailability",
          "description": "Retrieve whether an item is available in a given location",
          "inputSchema": {
            "json": {
              "type": "object",
              "properties": {
                "zipcode": {
                  "type": "string",
                  "description": "The zipcode of the location to check in"
                },
                "quantity": {
                  "type": "integer",
                  "description": "The number of items to check availability for"
                },
                "item_id": {
                  "type": "string",
                  "description": "The ASIN of item to check availability for"
                }
              },
              "required": [
                "item_id", "zipcode"
              ]
            }
          }
        }
      }
    ]
  },
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "I need to check whether there are twenty pieces of the following item available. Here is the item ASIN on Amazon: id-123. Please check for the zipcode 94086"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "reasoningContent": {
            "reasoningText": {
              "text": "The user wants to check how many pieces of the item with ASIN id-123 are available in the zipcode 94086"
            }
          }
        },
        {
          "toolUse": {
            "toolUseId": "getItemAvailability_0",
            "name": "getItemAvailability",
            "input": {
              "zipcode": "94086",
              "quantity": 20,
              "item_id": "id-123"
            }
          }
        }
      ]
    },
    {
      "role": "user",
      "content": [
        {
          "toolResult": {
            "toolUseId": "getItemAvailability_0",
            "content": [
              {
                "text": "[{\"name\": \"getItemAvailability\", \"results\": {\"availability\": true}}]"
              }
            ]
          }
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Yes, there are twenty pieces of item id-123 available at 94086. Would you like to place an order or know the total cost?"
        }
      ]
    }
  ]
}

工具呼叫資料的重要考量事項：

文件了解資料格式

SFT 支援文件理解任務的訓練模型。以下是範例輸入格式：

範例輸入

{
  "schemaVersion": "bedrock-conversation-2024",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What are the ways in which a customer can experience issues during checkout on Amazon?"
        },
        {
          "document": {
            "format": "pdf",
            "source": {
              "s3Location": {
                "uri": "s3://my-bucket-name/path/to/documents/customer_service_debugging.pdf",
                "bucketOwner": "123456789012"
              }
            }
          }
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Customers can experience issues with 1. Data entry, 2. Payment methods, 3. Connectivity while placing the order. Which one would you like to dive into?"
        }
      ],
      "reasoning_content": [
        {
          "text": "I need to find the relevant section in the document to answer the question.",
          "type": "text"
        }
      ]
    }
  ]
}

文件理解的重要考量：

影片了解 SFT

SFT 支援微調模型以進行影片理解任務。以下是範例輸入格式：

範例輸入

{
  "schemaVersion": "bedrock-conversation-2024",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What are the ways in which a customer can experience issues during checkout on Amazon?"
        },
        {
          "video": {
            "format": "mp4",
            "source": {
              "s3Location": {
                "uri": "s3://my-bucket-name/path/to/videos/customer_service_debugging.mp4",
                "bucketOwner": "123456789012"
              }
            }
          }
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "Customers can experience issues with 1. Data entry, 2. Payment methods, 3. Connectivity while placing the order. Which one would you like to dive into?"
        }
      ],
      "reasoning_content": [
        {
          "text": "I need to find the relevant section in the video to answer the question.",
          "type": "text"
        }
      ]
    }
  ]
}

了解影片的重要考量：

資料上傳指示

將訓練和驗證資料集上傳至 S3 儲存貯體。在配方的 run 區塊中指定這些位置：

## Run config
run:
  ...
  data_s3_path: "s3://<bucket-name>/<training-directory>/<training-file>.jsonl"
  

注意：將 <bucket-name>、<training-directory>、<training-file>、 <validation-directory>和 取代<validation-file>為實際的 S3 路徑。

注意：使用 Amazon Nova 2.0 的 SFT 目前不支援驗證資料集。如果提供驗證資料集，則會予以忽略。

建立微調任務

使用 run 區塊中的 model_type和 model_name_or_path 欄位來定義基本模型：

## Run config
run:
  ...
  model_type: amazon.nova-2-lite-v1:0:256k
  model_name_or_path: nova-lite-2/prod
  ...

SFT 調校參數

可使用 SFT 進行調校的參數包括：

執行組態

訓練組態

學習率排程器

最佳化工具組態

PEFT 組態

LoRA 調校 （當 peft_scheme 為 'lora' 時）

超參數指引

根據訓練方法，使用以下建議的超參數：

完整排名訓練

LoRA （低排名調整）

注意：根據資料集大小和驗證效能調整這些值。監控訓練指標以防止過度擬合。