SageMaker AI Serverless Model Customization Adds Full Fine-Tuning
Start here
Amazon SageMaker AI's Serverless Model Customization now supports Full Fine-Tuning (FFT), letting teams fine-tune large language models without provisioning GPUs, setting up clusters, or configuring distributed training, AWS said. Jobs can be configured and launched programmatically through the SageMaker Python SDK. AWS reported that on a Qwen3-4B base model trained with the Magicoder-Evol-Instruct-110K dataset, FFT reached 90.0 percent LLM-as-Judge semantic correctness on code generation at more than 100K training examples, outperforming LoRA. Switching between the two methods requires only changing TrainingType.FULL to TrainingType.LORA.
Generated from reports · updated 18 h ago
Report timeline
Follow the reports to see the event from different sides.
- AWS Machine Learning BlogFull Fine-Tuning (FFT) Now Available on SageMaker AI Serverless Model Customization
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT), letting teams fine-tune LLMs without GPU provisioning, cluster setup, or distributed-training configuration. On a Qwen3-4B base model trained with the Magicoder-Evol-Instruct-110K dataset, FFT reached 90.0 percent LLM-as-Judge semantic correctness on code generation at 100K+ training examples, outperforming LoRA.
Heat for this event
- Current, comparable range
- 6
- Peak, comparable range
- 10November 19 10:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.