FineEnvs/SmolDataEnvs
RL Environment • Updated • 5.39k • 2.46k • 50
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 • 201 -
FineEnvs/SmolDataEnvs-harbor-train
RL Environment • Updated • 1.92k • 2 -
FineEnvs/SmolDataEnvs-harbor-test
RL Environment • Updated • 556 -
FineEnvs/SmolDataEnvs-harbor-eval
RL Environment • Updated • 360
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