finetuning
Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.
- Version
- 1.0.0
Pinned to revision 4e8964e24a5a, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/finetuning/SKILL.md
- skills/finetuning/LICENSE
- skills/finetuning/code_templates/dpo.py
- skills/finetuning/code_templates/rlaif_builtin.py
- skills/finetuning/code_templates/rlaif_custom_prompt.py
- skills/finetuning/code_templates/rlvr.py
- skills/finetuning/code_templates/sft.py
- skills/finetuning/references/code_output_guide.md
- skills/finetuning/references/continuous_customization.md
- skills/finetuning/references/eula_links.md
- skills/finetuning/references/rlaif_guide.md
- skills/finetuning/references/rlvr_reward_function.md
- skills/finetuning/scripts/mlflow_reference.py
- skills/finetuning/templates/nova_rlvr_reward_function_source_template.py
- skills/finetuning/templates/rlvr_reward_function_source_template.py
Every link opens the file at its source, pinned to the revision this page describes.