Data · dataset · 2026

FineEnvs/SmolDataEnvs-harbor-train

Listed in Hugging Face Datasets

📊 SmolDataEnvs: Harbor (train) 5.5K+ RL tasks for hill-climbing small models in code and data science.

Description

A 2B model on these tasks. Left: what it optimises.

Right: 144 held-out tasks it never trains on. Two runs over the same 5,000 tasks: shuffled against a curriculum ordered easiest to hardest. The training suite: 5,000 hands-on data-analysis tasks.

Read the rest (1 more)

Each one drops an agent into a sandbox with a real dataset and a question, and asks it to explore the data… See the full description on the dataset page: huggingface.co/datasets/FineEnvs/SmolDataEnvs-harbor-train.

Topics

Stated by source: other
From keywords: Computer Science & AI · Reinforcement learning

Provenance · 1 source records, 9 field assertions

Source	Key	Last seen	Raw
Hugging Face Datasets	FineEnvs/SmolDataEnvs-harbor-train	7 d ago	JSON v1

Field	Assertion	Extractor	Evidence
access_level	source · Hugging Face	connector:huggingface@1.0.0	/gated
concepts[field].local:field:computer-science-ai	mapping · Hugging Face	connector:huggingface@1.0.0
concepts[task].hf_task:other	source · Hugging Face	connector:huggingface@1.0.0	/tags[task_categories:*]
created_date	source · Hugging Face	connector:huggingface@1.0.0
description	source · Hugging Face	connector:huggingface@1.0.0	/description
license	source · Hugging Face	connector:huggingface@1.0.0	/tags[license:*]
publication_date	source · Hugging Face	connector:huggingface@1.0.0
title	source · Hugging Face	connector:huggingface@1.0.0	/id
updated_date	source · Hugging Face	connector:huggingface@1.0.0

FineEnvs/SmolDataEnvs-harbor-train

Description

Links

Where it is published

Topics