> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trainy.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Experiments
> Experiments are an instance of a single run in Pluto.
# Creating an Experiment
Within Pluto, an experiment represent a singular instance of a tracked run. To create an experiment, invoke `pluto.init()` with the experiment `name` and a project `project`.
```python theme={null}
import pluto
pluto.init(name="gpt4o-vision", project="VLLM")
```
You can pass in configurations, e.g hyperparameters the `config` parameter
```python theme={null}
hyperparameters = {
"lr": 0.001,
"epochs": 1000,
}
pluto.init(
dir=".",
name="gpt4o-vision",
project="VLLM",
config=hyperparameters,
)
```
and this will be recorded in the experiment metadata.
## Tags
Tags are plaintext strings and a way for attaching small metadata about your run that will make it easy for you to group/filter runs in the webUI. Multiple tags can be specified for a single run.
To initialize a run with a particular tag, use the `tag` keyword argument which accepts `List[str]`
```
import pluto
pluto.init(
name="gpt4o-vision",
project="VLLM",
tags=["production", "v2", "baseline"]
)
```