training overview

train May 11, 2026 2 min read

a training run is where your environment and dataset come together: castform runs the rl training loop on gpus it provisions for you, and you end up with a fine-tuned model to evaluate and deploy. this page covers what happens during a run and which base models you can train.

what happens during a training run

  1. your environment class and datasets are uploaded to castform’s storage
  2. GPUs are provisioned (takes a few minutes)
  3. the training loop begins: the model generates completions, your reward function scores them, and the model updates its weights
  4. metrics and model outputs are reported to the console as the run progresses (updated periodically, not streamed live)

supported models

the platform currently supports four base models for fine-tuning. pass the model id via launcher_args.model when launching a run. per-token training rates for each model are on the pricing page.

modeldescription
Qwen/Qwen3.5-4Blightweight 4B parameter model. fast iteration, lower GPU cost. good default for experimentation.
Qwen/Qwen3-VL-4B-Instruct4B vision-language model. the choice for multimodal environments with image prompts and tools.
Qwen/Qwen3.5-35B-A3B35B mixture-of-experts model with 3B active parameters. stronger baseline, similar inference cost to the 4B.
google/gemma-4-26B-A4B-it26B mixture-of-experts model with 4B active parameters, from google. the option when you need a US-developed model.