README.md

metadata

title: RLM Arithmetic Training
emoji: 🔢
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
hardware: t4-small

GRPO + RLVR Arithmetic Training

Training Qwen3-0.6B-Base on simple arithmetic (2-digit addition/subtraction) using GRPO + RLVR.

Task

Solve arithmetic problems like:

• 47 + 35 = 82
• 92 - 17 = 75

Approach

• Model: Qwen/Qwen3-0.6B-Base
• Method: GRPO (Group Relative Policy Optimization) with RLVR (Reinforcement Learning with Verifiable Rewards)
• Reward: Exact match on answer
• Steps: 50

Expected Results

Base model (no math training) should perform poorly (<10%), trained model should improve significantly.