Fine-tune a model with LoRA — dragon

Writes a run directory, then launches the trainer as a background Python process. Returns immediately unless wait = TRUE. The run survives the R session; reopen it later with dragon_run().

Usage

dragon_train(
  dataset,
  model,
  lora = dragon_lora(),
  args = dragon_train_args(),
  hardware = dragon_hardware(),
  name = NULL,
  run_dir = NULL,
  runs_dir = dragon_runs_dir(),
  n_samples = 10,
  revision = NULL,
  trust_remote_code = FALSE,
  wait = FALSE
)

Arguments

dataset: A mapped dragon_dataset (see dragon_map()).
model: A Hugging Face model id such as "HuggingFaceTB/SmolLM2-135M-Instruct", or a local model directory. See dragon_presets().
lora: LoRA settings from dragon_lora().
args: Training settings from dragon_train_args().
hardware: Hardware settings from dragon_hardware().
name: Short label used in the run id. Defaults to the model name.
run_dir: Exact directory to use. Defaults to a timestamped directory under runs_dir.
runs_dir: Parent directory for runs. See dragon_runs_dir().
n_samples: Number of held-out rows to generate sample replies for at the end of training.
revision: Model revision (branch, tag, or commit) on the Hub.
trust_remote_code: Allow the model repository to run custom code.
wait: Block until training finishes.

Value

A dragon_run object.

Examples

if (FALSE) { # \dontrun{
run <- dragon_dataset(dragon_example_data()) |>
  dragon_map(prompt = "{subject}\n\n{body}", response = "reply") |>
  dragon_train("HuggingFaceTB/SmolLM2-135M-Instruct", wait = TRUE)
dragon_generate(run, "My order arrived damaged.")
} # }