> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trymonte.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Train open-weight models with SFT, DPO, GRPO, or distillation

Train an open-weight model on a team's own tasks. A training run takes a training config, training data, and a starting point, and saves checkpoints as it trains. Every checkpoint can be scored on the experiment's evals and deployed.

```bash theme={null}
monte train support-triage \
  --config triage-sft \
  --data support-replies \
  --steps 200 \
  --from-base
```

| Flag | Description |
| - | - |
| `--config` | The [training config](https://docs.trymonte.ai/training/configs.md): model, method, LoRA, batch size, learning rate |
| `--data` | The training data: a [dataset](https://docs.trymonte.ai/datasets/overview.md) or a [training environment](https://docs.trymonte.ai/environments/overview.md) |
| `--steps` | The number of steps in this run |
| `--from-base` or `--parent <run>/<step>` | The starting point: the base model, or a checkpoint |

The run saves a checkpoint every 50 steps and at its last step, so this run ends with `train-07/200`. A run starts only after every eval in the experiment has a [baseline](https://docs.trymonte.ai/evaluation/experiments.md#take-the-baselines).

## Choose a Method

The training config sets the method. The method sets the kind of training data.

| Method | Signal | Training data | Use when |
| - | - | - | - |
| [SFT](https://docs.trymonte.ai/training/sft.md) | Example responses | Dataset, `--kind sft` | The target output can be written down |
| [DPO](https://docs.trymonte.ai/training/dpo.md) | Pairs of a preferred and a rejected response | Dataset, `--kind preference` | Reviewers can pick the better of two outputs |
| [GRPO](https://docs.trymonte.ai/training/grpo.md) | The grader's score on the model's own samples | Training environment | A grader, in code or with an open-weight judge, can score an output |
| [Distillation](https://docs.trymonte.ai/training/distillation.md) | The teacher's next-token distributions on the student's own samples | Training environment | A larger model already does the task well |

## Choose Full Fine-Tune or LoRA

A `lora` block in the [training config](https://docs.trymonte.ai/training/configs.md) trains low-rank adapters, and the base weights do not change. Without the block, the run trains every weight.

| | Full fine-tune | LoRA |
| - | - | - |
| Checkpoint | A full model | An adapter |
| Serving | One deployment for each checkpoint | Many adapters on one base deployment. See [Serving](https://docs.trymonte.ai/serving/deploy.md). |
| Use when | The task needs the largest change to the model | Several variants of one model, or a fast first run |

## Continue From a Checkpoint

`--parent train-07/200` starts a new run from that checkpoint with any config and data, and `monte train resume` continues a run for more steps. A LoRA run with `--parent` on a LoRA checkpoint continues the same adapter, so it serves on the same base. Several runs from one parent give several adapters on one base.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.