FineEnvs/SmolDataEnvs
RL Environment • Updated • 5.39k • 4.7k • 80
SmolDataEnvs
5.5K+ RL tasks for hill-climbing small models in code and data science. Deterministic grading, no LLM judge.
-
-
FineEnvs/SmolDataEnvs-sft
Viewer • Updated • 4.68k • 387 • 2 -
FineEnvs/SmolDataEnvs-harbor-train
RL Environment • Updated • 5.53k • 4 -
FineEnvs/SmolDataEnvs-harbor-test
RL Environment • Updated • 1.38k -
FineEnvs/SmolDataEnvs-harbor-eval
RL Environment • Updated • 1.1k
SmolDataEnvs train logs
📈GRPO training logs for Qwen3.5 on SmolDataEnvs
Note Trackio logs for the GRPO runs behind the curves on the dataset cards.
-
FineEnvs/SmolDataEnvs-multiharness-sft
Preview • Updated • 283 • 2
SmolDataEnvs Multi-harness | SETA Whitebox
🧪Answer dataset questions and view scoring results
Note Start here: solve a data task in the SETA whitebox playground. These same Bash tools are used by GRPO.
SmolDataEnvs Multi-harness | Native OpenCode
🧪Run OpenCode tasks and view grading results
Note Native OpenCode blackbox. Standalone environment source, Task API and typed training traces for AsyncGRPO.
SmolDataEnvs Multi-harness | Harbor
🧪Explore and manage tasks in the Harbor agentic environment
Note Harbor multi-harness blackbox. Browse tasks, connect a model, run a harness and inspect live traces.