SageMaker AI serverless customization adds full fine-tuning
Understand this story
Amazon SageMaker AI's Serverless Model Customization now supports full fine-tuning (FFT). AWS says users can complete full fine-tuning without configuring GPUs, setting up clusters, or setting up distributed training themselves. Users can configure and launch training and evaluation jobs programmatically via the SageMaker Python SDK. AWS says this approach delivers higher model quality without managing infrastructure.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogFull Fine-Tuning (FFT) on SageMaker AI Serverless Model Customization
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT), which updates all model parameters to overcome the low-rank limits of LoRA and requires no GPU provisioning or cluster setup. In experiments fine-tuning Qwen3-4B on the 110K-example Magicoder-Evol-Instruct-110K code dataset, FFT reached 90.0 percent LLM-as-Judge semantic correctness at 100K+ training examples, though results were highly sensitive to hyperparameters, with aggressive learning rates (LR ≥ 5e-5) causing catastrophic forgetting. The post also notes LoRA slightly outperformed FFT on LLM-as-Judge (81.5 vs. 79.5 percent) and that both underperformed the base model on MATH exact match.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 19 10:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.