Training Methods
Every method is YAML-driven, runs through the same distributed parallelism system, and ships example configs under examples/.
Methods at a glance
Family overviews: Preference · GRPO.
Column types and per-script defaults: Dataset Formats. Scripts and their flags: Scripts Reference. Undecided: Choosing a method.
Vision-language support
SFT, DPO, KTO, SMPO, both off-policy distillation scripts and reward modeling (on families with a sequence-classification head) take images, PaliGemma only through SFT and distillation; classification, embedding and the GRPO family are text-only. One script serves both modalities — the model class follows the checkpoint and the data path follows the run, so a text-only dataset on a multimodal checkpoint trains through the text pipeline.
Per-method rules: Modality support. text_only_model: true loads a multimodal checkpoint through its text-only sibling (field reference).
Parallelism support
No trainer refuses EP, TP or ETP (Trainer Compatibility). Context parallelism is declare-to-enable per trainer (SUPPORTS_CP): SFT, SMPO and offline GRPO full fine-tuning support it; online and environment GRPO do not.
Pipeline parallelism is declare-to-enable the same way (PP_REFUSAL = None): SFT, SMPO, DPO and KTO (precompute-only), offline GRPO, reward and classification support it (Pipeline Parallelism).
Full trainer × mode matrix: Trainer Compatibility.
Experiment tracking
Every script reports to the backend named by report_to, logging loss, learning rate and gradient norm automatically. The toolkit callbacks add throughput, MoE expert load, eval-time generations and parameter stats (Training Callbacks).
YAML
report_to: wandb # wandb | clearml | tensorboard | none
run_name: my-sft-run # optional; names the run in the trackerSource on GitHubUpdated 18 November 2026