---
title: Run on non-adapted data | Adaption
description: Upload a training-ready prompt/completion file and send it directly to AutoScientist.
---

Use [raw dataset processing](/api/python/resources/datasets/methods/create/index.md) when a tabular file already contains training-ready prompt and completion columns and you want AutoScientist to train on those rows as-is. This skips Adaptive Data’s adaptation pipeline.

For best results, [adapt your data first](/adaptive-data/overview/index.md). Use raw processing only when training on the original rows is intentional.

Raw processing supports CSV, JSON, JSONL, and Parquet files. Set `processing_mode` to `raw` and [map both required source columns](/adaptive-data/select-columns/index.md) when creating the dataset.

## Upload and train

This example uploads a CSV whose `instruction` and `response` columns contain the training pairs:

```
import hashlib
from pathlib import Path


import httpx
from adaption import Adaption


client = Adaption()


path = Path("training_data.csv")
data = path.read_bytes()


dataset = client.datasets.create(
    source={
        "name": path.stem,
        "file_format": "csv",
        "processing_mode": "raw",
        "column_mapping": {
            "prompt": "instruction",
            "completion": "response",
        },
    },
)


response = httpx.put(dataset.upload_instructions.url, content=data)
response.raise_for_status()


client.datasets.upload.complete_by_id(
    dataset.dataset_id,
    file_size_bytes=len(data),
    sha256=hashlib.sha256(data).hexdigest(),
)
client.datasets.wait_for_completion(dataset.dataset_id)


run = client.autoscientist.create(dataset_id=dataset.dataset_id)
run = client.autoscientist.wait_for_completion(run.id)


if run.status == "failed":
    raise RuntimeError(f"failed: {run.error}")
if run.status != "succeeded":
    raise RuntimeError(f"Run ended with status: {run.status}")


print(run.id, run.best_win_rate)
```

Do not call `client.datasets.run` for this workflow: raw processing makes the uploaded dataset ready for AutoScientist directly. The `column_mapping` above refers to the original file headers; an AutoScientist `column_mapping`, if supplied later, refers to the processed dataset schema.

See [Running AutoScientist](/autoscientist/running-autoscientist/index.md) for polling, cancellation, and status details. For endpoint details, see the [`datasets.create`](/api/python/resources/datasets/methods/create/index.md) and [`autoscientist.create`](/api/python/resources/autoscientist/methods/create/index.md) references.