Downloads · 30 days
0
tinker-rl-bench-frontier_gsm8k_nemotron-120b
arvindcr4/tinker-rl-bench-frontier_gsm8k_nemotron-120b
tinker-rl-bench-frontier_gsm8k_nemotron-120b is a reinforcement learning model from arvindcr4. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for tinker. The card lists the license as mit.
GRPO experiment from TinkerRL-Bench world-class experiment suite.
Access
Public
Updated Apr 19, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.9 KB · 64%
At a glance
- Task
- Reinforcement Learning
- Library
- tinker
- License
- mit
- Access
- Public
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026
- SHA
- 3a695b8b
Base models
Datasets
Model card
From the Hugging Face model README
frontier_gsm8k_nemotron-120b
GRPO experiment from TinkerRL-Bench world-class experiment suite.
Training Details
- Base model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- Method: GRPO (Group Relative Policy Optimization)
- Platform: Tinker API v0.18.1
- Task: gsm8k
- Seed: 42
- LoRA rank: 16
- Learning rate: 1e-05
- Group size: 4
- Steps: 20
Results
- First-5 avg reward: 17.5%
- Last-10 avg reward: 16.2%
- Peak reward: 87.5%
- Zero-loss steps: 70%
- Tinker Run ID: 657a920a-9e74-55d2-9354-71a6ec2f1f61:train:0
Reward Trace
[
0.0,
0.0,
0.875,
0.0,
0.0,
0.0,
0.125,
0.5,
0.375,
0.0,
0.125,
0.25,
0.0,
0.0,
0.25,
0.0,
0.0,
0.0,
0.5,
0.5
]
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}
}
- Task
- Reinforcement Learning
- Library
- tinker
- License
- mit
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026