Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Arena Documentation
Logo
Arena Documentation

Getting started

  • Getting started
  • Quickstart
  • Classic vs Advanced Training
  • Balance and plans

Tutorials

  • Tutorials
  • Environments
    • Upload a custom environment
    • Upload a language-based environment
  • Datasets
    • Upload a reasoning dataset
    • Upload a preference dataset
    • Upload an SFT dataset
    • Upload an object detection dataset
  • Experiments
    • Create a training project
    • Run an SFT experiment
    • Run a Preference experiment
    • Run a Reasoning experiment
    • Run a Multi-turn LLM experiment
    • View results and checkpoints
    • Run a Classic RL experiment
  • Agents
    • Deploy and invoke an agent
  • Account
    • Billing and balance

Account & platform

  • Account
  • Profile and CLI keys
  • Account deletion
  • Organizations
  • Billing
  • Usage and statements

Projects & experiments

  • Projects
  • Experiments
  • Train, halt, and resume
  • Logs and metrics

Experiment wizard

  • Experiment wizard overview
  • Resources
  • Environment
  • Agent
  • Training
  • HPO

Environments

  • Environments
  • Custom environments
  • Validation and profiling

Datasets

  • Datasets
  • Reasoning datasets
  • Preference datasets
  • SFT datasets
  • Tabular datasets
  • Non-tabular datasets

Training

  • Training
  • How evolutionary hyperparameter optimization works
  • Classic RL algorithms
  • LLM algorithms
  • Supervised training
  • Training settings

Results & pipelines

  • Results
  • Checkpoints
  • Pipelines

Agents & inference

  • Agents
  • Create and deploy an agent
  • Invoke an agent
  • Inference contract

Bring your own compute (BYOC)

  • Bring your own compute (BYOC)
  • Install a cluster
  • Bring your own compute (BYOC) resource classes
  • Bring your own compute
  • Migrating to enterprise BYOC

Arena CLI

  • Arena CLI
  • CLI authentication
  • CLI commands
  • Bring your own compute (BYOC) CLI

Reference

  • Glossary
  • Algorithms reference
  • Experiment statuses
  • Plans and permissions
  • Finding your way in Arena

Troubleshooting

  • Troubleshooting
Back to top

DatasetsΒΆ

Create language, tabular and non-tabular datasets used in Advanced Training.

Tutorial

What you will do

Upload a reasoning dataset

Create a Language Reasoning dataset (Question / Answer)

Upload a preference dataset

Create a Language Preference dataset (Prompt / Chosen / Rejected)

Upload an SFT dataset

Create a Language SFT dataset (Prompt / Target)

Upload an object detection dataset

Create a non-tabular object detection dataset with mask targets, then preprocess it (Enterprise)

Next
Upload a reasoning dataset
Previous
Upload a language-based environment
Copyright © 2026, AgileRL