arvindcr4/tinker-rl-bench-scale_gsm8k_llama-8b-inst

scale_gsm8k_llama-8b-inst

GRPO experiment from TinkerRL-Bench world-class experiment suite.

Training Details

• Base model: meta-llama/Llama-3.1-8B-Instruct
• Method: GRPO (Group Relative Policy Optimization)
• Platform: Tinker API v0.18.1
• Task: gsm8k
• Seed: 42
• LoRA rank: 32
• Learning rate: 3e-05
• Group size: 8
• Steps: 30

Results

• First-5 avg reward: 97.5%
• Last-10 avg reward: 84.4%
• Peak reward: 100.0%
• Zero-loss steps: 43%
• Tinker Run ID: 488bbb2e-aa35-5431-b4a5-793f68b6bc49:train:0

Reward Trace

[
  1.0,
  0.875,
  1.0,
  1.0,
  1.0,
  0.625,
  1.0,
  1.0,
  0.875,
  0.875,
  1.0,
  1.0,
  0.9375,
  0.75,
  1.0,
  0.375,
  0.8125,
  0.875,
  0.875,
  0.75,
  0.875,
  0.6875,
  0.75,
  0.4375,
  1.0,
  1.0,
  0.8125,
  1.0,
  0.875,
  1.0
]

Citation

@misc{tinker-rl-bench-2026,
  title={TinkerRL-Bench: A Unified Benchmark for RL Post-Training},
  author={Arvind C R and Sandhya Jeyaraj and Madhu Kumara L and Mohammad Rafi and Dhruva N Murthy and Arumugam K},
  year={2026},
  url={https://github.com/arvindcr4/tinker-rl-lab}
}