在不管理 GPU 的情况下，宣布自定义 SageMaker AI 模型的新方式

人工智能

在不管理 GPU 的情况下，宣布自定义 SageMaker AI 模型的新方式

从人工智能中获得实际结果的公司，使用强化学习等训练后技术，一个在你的商业环境，产品目录，或临床词汇方面受过训练的模型，对于你的任务来说会更准确，运行成本也会更低。 当你建立agents时，你的数据，工作流程，评价，以及成功标准也决定了模型的行为方式。

然而，模式定制很难。 您必须选择正确的技术，设置和管理GPU基础设施，并为agents构建多回合强化学习的环境。 我们发布 Amazon SageMaker AI无服务器模型定制以应对这些挑战，而今天，我们正在扩展它

有了培训班，你就能控制培训后的逻辑，而不管理基本的基础设施。 您写和协调训练循环，包括自定义丢失函数或奖励信号。 SageMaker AI处理GPU分配，分布式执行，故障恢复，以及检查站存储。

定制而无需基础设施管理麻烦

使用 SageMaker AI 无服务器模式定制，您不会选择实例类型、 管理集群或写入分布式训练配置。

我们不想限制你。 可以使用SFT,DPO,RLVR,RLAIF等技术，或多转RL. 通过连续定制，您可以选择使用Low-Rank适应(LoRA)或全微调和链技术一起更新的模型的多少。

我们不希望你浪费时间。 我们的SageMaker AI培训课程提供实例和使用案例，以及模型定制的agent技能。 agent处理数据准备、技术选择、培训、评价和部署。 agent在工作的地方工作，在SageMaker Studio,Kiro,Claude Code,Codex，或GitHub Copilot工作。

“我们采用了SageMaker AI Serverless培训课程，以建立一个保健权利要求-拒绝分级模式，经验从第一天起就验证了这一平台。 低水平的API表面，对前向和后向通道的直接控制，采样，优化步骤给了我们的科学家一个精细的控制，他们需要针对一个高要求的，精度的关键使用案例进行强化学习。 训练课程为我们提供了推动生产级业绩的正确原始人。”

——罗布·贡塔雷克，数据科学高级副总裁，想象软件

写你自己的训练后循环

agent培训的一个重要转变是转向多回合强化学习。 例如，图书旅行的agent，三进制支持门票，或运行一个多步骤的研究任务，需要几轮互动才能判断它是否达到了正确的结果。

然而，训练循环会很快变得复杂。 你可以在一套基础设施上训练模型，对另一套基础设施进行推论以生成响应，对这些响应进行评分，并将结果反馈到下一次更新中。 每个阶段都需要不同的计算，并把它们通过单独的工具和集群新增工作连接起来。

SageMaker AI已经提供了多回合的RL作为管理，没有服务器的技术。 但我们听到客户想要定义自己的损失功能，形状奖励信号，或者一个循环的RL级。 培训班给了你这种灵活性。

“我们用SageMaker AI Serverless Trains对gpt-oss-20b进行了微调，使其具有代理性，多转动工具，反对我们的Amazon Neptune知识图表——平台为我们处理基础设施。 设置刚刚奏效，没有手动调音，也没有出门的纠葛。 检查点和检查点是突出的：从确切的步骤恢复是完全可靠的。 它给我们的开发者带来了他们想要的灵活性，同时把业务负担从他们的盘子里卸下来。”

- Nitin Wagh，首席执行官，Karini AI

如何运作

您的代码在您的环境中运行训练循环和奖励功能，并将agent与其工具或模拟器连接起来。 培训班执行GPU重力工作：一个采样器生成响应，一个训练员计算梯度并更新模型权重。 确切的序列取决于你所写的算法。

例如，让我们看看集团相对政策优化(GRPO)的执行情况。 GRPO是一种强化的学习方法，可以生成对同一快件的数个响应，计分，并使用它们的相对性能来更新模型。 一个通过循环这样的工作：

- 样本响应 – 您的循环要求采样者使用当前模型为每个提示生成多个响应。

- 记分他们您的奖励功能在您环境中使用验证器、奖励模型或测试带对每个响应进行评分。

- 更新模型 – 您的循环将分数寄回给教练。 前置 backward () 使用它们计算梯度，优化 step () 将更新应用到模型权重。

- 刷新和重复 – 您的循环要求会话用更新的权重刷新采样器，然后开始下一批。 你的代码重复这些步骤直到训练完成。

你付了SageMaker AI的代币计数器停止时，您的奖励函数会在环境中评分一个批次，而且没有保留能力。

控制您的数据和模型

每个会话都使用您创建的AWS身份与访问管理(IAM)执行角色，您可以添加自己的AWS密钥管理服务(AWS KMS)密钥和虚拟私密云(VPC)配置。 您的数据保留在您选择的 Amazon 简易存储服务( Amazon S3) 区域中的桶中，您的检查站也在那里降落。

我们不会用你的数据或定制的重量来训练另一个模型。 在部署前，可以评估模型的准确性，偏差性，以及安全性。 部署后，可以应用护栏，用Amazon云表进行监控。

你可以继续使用你的团队已经拥有的治理程序。

今天开始

在SageMaker AI无服务器模式定制培训课程上写你自己的训练循环，今天已有gpt-oss-20b,gemma-4-31B-it,Qwen3.6-27B,Qwen3.8-27B的支持。

两个开始的方法：

- 在您的 IDE 中：安装 SageMaker Python SDK (在 Linux 或 macOS 上使用 Python 3.10 到 3.12) 复制烹饪本，并开始开发。

- 在SageMaker Studio：发布，20秒内即时使用AI开发环境。 签名，打开笔记本，连接您的编码 agent( Kiro, Claude Code, Codex，或 Copilot)，下载 agent 的技能和烹饪本，你准备开始。

资源

培训班文件

本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。

Artificial Intelligence

Announcing new ways to customize models with SageMaker AI, without managing GPUs

Companies getting real results from AI aren’t only using foundation models (FMs) off the shelf. They’re customizing open-weight models using post-training techniques such as reinforcement learning. A model trained on your business context, product catalog, or clinical vocabulary will be more accurate for your task and cost less to run. When you build agents, your data, workflows, evaluations, and success criteria also shape how the model behaves.

However, model customization is difficult. You must choose the right technique, set up and manage GPU infrastructure, and, for agents, build environments for multi-turn reinforcement learning. We launched Amazon SageMaker AI serverless model customization to solve these challenges, and today, we’re expanding it with the general availability launch of training sessions.

With training sessions you get control over the post-training logic without managing the underlying infrastructure. You write and coordinate the training loop, including custom loss functions or reward signals. SageMaker AI handles GPU allocation, distributed execution, fault recovery, and checkpoint storage.

Customize without the hassles of infrastructure management

With SageMaker AI serverless model customization, you don’t choose instance types, manage clusters, or write distributed training configuration.

We didn’t want to limit you. You can use techniques such as SFT, DPO, RLVR, RLAIF, or multi-turn RL. You can choose how much of the model to update with Low-Rank Adaptation (LoRA) or full fine-tuning and chain techniques together through continuous customization.

We didn’t want you to waste time. Our SageMaker AI training sessions cookbook provides examples and use cases, along with model customization agent skills. You describe your use case, and the agent handles data prep, technique choice, training, evaluation, and deployment. The agent works where you work, in SageMaker Studio, Kiro, Claude Code, Codex, or GitHub Copilot.

“We adopted SageMaker AI Serverless Training Sessions to build a healthcare claim-denial triage model, and the experience validated the platform from day one. The low-level API surface, direct control over the forward and backward passes, sampling, and the optimizer step gave our scientists the fine-grained control they need to pursue reinforcement learning on a demanding, accuracy-critical use case. Training Sessions gives us the right primitives to push toward production-grade performance.”

— Rob Gontarek, Senior Vice President, Data Science, ImagineSoftware

Write your own post-training loop

One important shift in agent training is toward multi-turn reinforcement learning. For example, an agent that books travel, triages support tickets, or runs a multi-step research task needs several rounds of interaction before you can judge whether it reached the right outcome.

However, the training loop can get complicated quickly. You may train the model on one set of infrastructure, run inference on another to generate responses, score those responses, and feed the results into the next update. Each stage needs different compute, and connecting them across separate tools and clusters adds work.

SageMaker AI already offers multi-turn RL as a managed, serverless technique. But we heard from customers who wanted to define their own loss functions, shape reward signals, or RL stages in one loop. Training sessions give you that flexibility.

“With SageMaker AI Serverless Training Sessions, we fine-tuned gpt-oss-20b for agentic, multi-turn tool calling against our Amazon Neptune knowledge graph — and the platform handled the infrastructure for us. Setup just worked, with no manual tuning and no out-of-memory wrangling. Checkpoint-and-resume was a standout: resuming from an exact step was completely reliable. It gave our developers the flexibility they wanted while taking the operational burden off their plate.”

— Nitin Wagh, CEO, Karini AI

How it works

Your code runs the training loop and reward function in your environment and connects the agent to its tools or simulators. The training session performs the GPU-heavy work: a sampler generates responses, and a trainer calculates gradients and updates the model weights. The exact sequence depends on the algorithm you write.

For example, let’s look at Group Relative Policy Optimization (GRPO) implementation. GRPO is a reinforcement learning method that generates several responses to the same prompt, scores them, and uses their relative performance to update the model. One pass through the loop works like this:

- Sample responses – Your loop asks the sampler to generate several responses for each prompt using the current model.

- Score them – Your reward function scores each response in your environment using a verifier, reward model, or test harness.

- Update the model – Your loop sends the scores back to the trainer. forward_backward() uses them to calculate gradients, and optim_step() applies the update to the model weights.

- Refresh and repeat – Your loop asks the session to refresh the sampler with the updated weights, then starts the next batch. Your code repeats these steps until training is complete.

You pay for the tokens SageMaker AI processes. The meter stops while your reward function scores a batch in your environment, and there is no capacity to reserve.

Keep control of your data and models

Each session uses an AWS Identity and Access Management (IAM) execution role that you create, and you can add your own AWS Key Management Service (AWS KMS) key and virtual private cloud (VPC) configuration. Your data stays in your own Amazon Simple Storage Service (Amazon S3) buckets in the AWS Region that you choose, and your checkpoints land there too.

We don’t use your data or your customized weights to train another model. Before deployment, you can evaluate the model for accuracy, bias, and safety. After you deploy, you can apply guardrails and monitor it with Amazon CloudWatch.

You can keep using the governance processes your teams already have.

Get started today

Write your own training loop on SageMaker AI serverless model customization training sessions, available today with support for gpt-oss-20b, gemma-4-31B-it, Qwen3.6-27B, and Qwen3.8-27B.

Two ways to get started:

- In your IDE: Install the SageMaker Python SDK (on Linux or macOS with Python 3.10 to 3.12), clone the cookbook, and start developing.

- In SageMaker Studio: Launch a ready-to-use AI development environment in under 20 seconds. Sign in, open a notebook, connect your coding agent (Kiro, Claude Code, Codex, or Copilot), download the agent skills and cookbook, and you’re ready to begin.

Resources

Training sessions documentation

Auto-fetched and translated by AI Atlas. All rights belong to the original author.