---
title: AutoScientist App Walkthrough | Adaption
description: Select training data, review AutoScientist's proposed model and recipe, launch training, and interpret the result in the Adaption app.
---

[AutoScientist](/autoscientist/overview/index.md) co-optimizes training data and the model-training recipe. It runs the training and evaluation loop for you, producing an adapted model rather than only an adapted dataset.

## Before you start

Sign in at [adaptionlabs.ai/app](https://adaptionlabs.ai/app) and open **AutoScientist**.

Select a dataset that has completed an Adaptive Data run. You can also select multiple datasets and consolidate them into a new dataset for training; consolidation changes the total row count and creates a new dataset on the dashboard.

![Select a dataset for AutoScientist](/auto-scientist/ASEX1.png)

If you need to train on original rather than enhanced rows in the app, select the original columns during column mapping. As a separate programmatic alternative, [raw dataset processing](/autoscientist/run-on-non-adapted-data/index.md) uploads training-ready prompt and completion columns directly to AutoScientist and skips the Adaptive Data pipeline.

## Step 1 | Choose a model-size range

Tell AutoScientist whether your deployment has a [model-size constraint](/autoscientist/running-autoscientist#constrain-model-size/index.md).

![Choose an AutoScientist model-size range](/auto-scientist/AS-EX-2.png)

- **All sizes** allows AutoScientist to optimize for quality without a size restriction. Choose it when your serving infrastructure can support larger models.
- **Tiny AutoScientist** restricts training to models under 10B parameters. Choose it for on-device use, a limited inference budget, a single-device target, or lower latency.

Model size affects quality, serving cost, latency, and hardware requirements. Apply a known deployment constraint now rather than discovering after training that the model cannot run in its target environment.

## Step 2 | Select training columns

Choose the **Prompt** and **Completion** columns used for training. The preview compares original and enhanced values, and you can choose either version.

![Compare and select the AutoScientist training columns](/auto-scientist/AS_col.png)

For a visual-language-model dataset, the app also displays the **Image Context** column. That mapping cannot be edited. Multimodal AutoScientist jobs require more than 1,000 rows.

![Review the read-only image context mapping](/auto-scientist/AS_imagecontext.png)

Enable reasoning only if the dataset has an appropriate reasoning column and you need reasoning fine-tuning. This narrows the set of eligible models because only some models support it.

## Step 3 | Configure augmentation

AutoScientist evaluates the selected data and may offer two independent, optional [augmentation](/autoscientist/data-augmentation/index.md) expansions:

- **Domain dataset expansion** appears when the dataset has fewer than 20,000 datapoints. Move the slider to choose a target size; the app updates the required credits and resulting row count.
- **Diversity dataset expansion** appears when the data is not diverse enough. Its slider adds general-purpose datapoints and also updates cost and size live.

Treat these as separate decisions. For example, a 12,000-row legal dataset might benefit from domain expansion without general-purpose expansion if its coverage is narrow but its examples are already varied.

## Step 4 | Review the training recipe

AutoScientist proposes a [complete training recipe](/autoscientist/recommended-hyperparameters/index.md). Every field remains editable before confirmation:

- **Algorithm:** LoRA or full fine-tuning.
- **Epochs:** the number of passes through the training dataset.
- **LoRA rank (`r`):** adapter capacity; higher ranks use more memory and compute.
- **Alpha:** scales the LoRA adapter’s contribution to the base model.
- **Model name:** the base model to fine-tune.
- **Target layers:** modules such as `q_proj`, `v_proj`, or all linear layers that receive LoRA adapters.
- **Optimizer and schedule:** controls parameter updates and how the learning rate changes. A linear schedule decays steadily; a cosine schedule slows the decay near the end.
- **Warmup ratio:** the fraction of training steps used to raise the learning rate gradually from zero.
- **Gradient clipping:** caps gradient magnitude to reduce unstable updates.

Review the model and algorithm first because they determine which other settings are valid. Keep the proposed values unless you have a reason to override them.

## Step 5 | Confirm and launch training

On **Confirm your optimization choices**, inspect the raw JSON representation of the exact configuration. Use **Copy** to save it or **Edit** to return to the configuration.

The final order summary separates the cost of:

- Domain dataset expansion.
- Diversity dataset expansion.
- AutoScientist training.

Confirm the order, then [track the run and its status](/autoscientist/running-autoscientist#wait-for-completion/index.md) from the **AutoScientist** section of the dashboard.

## Step 6 | Interpret the results

When the run completes, [interpret the results](/autoscientist/interpreting-results/index.md) on the page showing the trained model ID and:

- [**Weights export**](/autoscientist/download-the-model/index.md) for downloading the trained model.
- **AutoScientist Config** for reviewing the configuration that produced it.
- **Training Winrates** for comparing the adapted model with its base model.
- **Train/Eval Metrics** for diagnosing training over time.

### Training win rate

The win-rate chart reports head-to-head evaluation results. For example, an adapted-model score of 70 means it won approximately 70% of comparisons against the original base model on the evaluation data.

### Loss

Training loss measures prediction error on training data; validation loss measures error on held-out data. Read them together to judge whether the model is learning patterns that generalize or merely overfitting.

### Learning rate

The learning-rate chart shows the update step size over training steps. Its shape reflects the selected schedule and warmup.

### Gradient norm

Gradient norm measures the magnitude of weight-update gradients. Sudden spikes can indicate instability, while a stable or flattening curve can indicate that optimization has settled.

## Common issues

- **Flat or negative win rate:** use at least a 7–8B model, consider more epochs, and review whether augmentation toward 20,000 datapoints is appropriate.
- **Need to publish on Hugging Face:** [download the model](/autoscientist/download-the-model/index.md), create a blank Hugging Face repository, and upload the files through its web UI.
- **Unclear whether a job is queued or stuck:** check the **AutoScientist** tab for status and the **Measure** tab for metrics. If it remains unchanged well beyond the expected duration, [contact support](/resources/support/index.md).
- **Need to train on original rows:** select the original prompt and completion columns instead of the enhanced versions.

## Next steps

- [Automate an AutoScientist run](/autoscientist/running-autoscientist/index.md)
- [Download the trained model](/autoscientist/download-the-model/index.md)
- [Review recommended hyperparameters](/autoscientist/recommended-hyperparameters/index.md)
- Browse the current request and response schema in the [API reference](/api/python/index.md).
