Blocks
trainer
Supervised fine-tuning on tracer's SFT data
trainer is the supervised fine-tuning stage. It reads LLaMA-Factory LF-format SFT data produced by tracer, then trains a base model with LLaMA-Factory + DeepSpeed ZeRO-3 across 8 GPUs.
Full docs: swe-trainer-docs.pages.dev/docs
Long-form docs live there
The trainer block ships its own complete documentation site — getting started, core concepts, the trajectory→ShareGPT data pipeline (scaffolds, scoring, evaluator-leak filtering), training (configuration, results, and artifacts), the live dashboard, and the full reference. This page is just an orientation; follow the link above for everything else.
At a glance
- Inputs:
source,conversion,model,training,infrastructure,credentials. The training data dependency is typically wired fromtracer.output.sft_data_dir. - Output:
checkpoint_path—subblock/trainer/artifacts/model/<run>/(consumed byrlas the starting actor). - Runs: Local (8× GPU). Long-running.
How to run
/trainer:setup # install LLaMA-Factory, register dataset, fill defaults
/trainer:check # preflight: GPUs, DeepSpeed config, dataset, base model
/trainer:run # launch training
/trainer:dashboard # parse the latest training log + WandB URLReference
- Block contract:
subblock/trainer/CLAUDE.md - Full docs site: swe-trainer-docs.pages.dev/docs