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

# sf eval

> Run a recipe's native evaluation

```bash theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
sf eval my-grpo --model Qwen/Qwen2.5-7B
```

跑 recipe 所属框架自带的评测——NeMo-RL 的 evaluation config、verl 的 SFT 验证循环。
这是框架自己那套「现在跑得怎么样」，用的是框架自己的口径。

这和 [`sf bench`](/zh-Hans/cli/bench) 不同：后者通过外部 harness 跑学术标准基准，
结果能跨 run、跨方法、跨别人的模型比较。在一个方法内部迭代时用 `sf eval`，要做比较时用 `sf bench`。

它也能在训练后自动执行：

```bash theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
sf submit my-grpo --profile h200:8 --then eval
```

## `sf eval`

Run a recipe's native evaluation

```bash theme={"theme":{"light":"github-light","dark":"github-dark-dimmed"}}
sf eval <EXP> [options]
```

| 参数    | 说明                               |
| ----- | -------------------------------- |
| `EXP` | Experiment name or path (**必填**) |

| 选项                     | 说明                                                                                        |
| ---------------------- | ----------------------------------------------------------------------------------------- |
| `--run-id`             | VeRL SFT: the training run id that receives the validation samples                        |
| `--model`              | NeMo-RL or VeRL SFT: HF model path / Hub id                                               |
| `--eval-config`        | NeMo-RL: explicit evaluation config path                                                  |
| `--data`               | verl: explicit evaluation data path                                                       |
| `--step` `<int range>` | VeRL SFT: the training step the exported checkpoint belongs to                            |
| `--profile`            | Hardware profile (managed by the server registry; `sf status` lists the available values) |
| `--allow-dirty`        | Allow uncommitted changes in the working tree                                             |
| `--dry-run`            | Only print the command that would be submitted                                            |