Downloads · 30 days
0
logan7000/mllm-mmr1-gt-gemma3-12b-mmupt-full
mllm-mmr1-gt-gemma3-12b-mmupt-full is a machine learning model from logan7000. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
GRPO with ground-truth rewards, MMR1-Math-RL-Data-v0, 481 steps (mmupt recipe: beta=0.01, 10 generations/prompt, cap 2048, T=0.7, 12 prompts/update).
Downloads · 30 days
0
Access
Public
Updated Aug 22, 2026
Repo size
48.8 GB
Likes
0
Public
Click a slice to open those files.
.safetensors48.7 GB · 100%
From the Hugging Face model README
GRPO with ground-truth rewards, MMR1-Math-RL-Data-v0, 481 steps (mmupt recipe: beta=0.01, 10 generations/prompt, cap 2048, T=0.7, 12 prompts/update).
| folder | step | note |
|---|---|---|
best/ | 100 | best in-loop val (eval_reward = 0.375) |
endpoint/ | 481 | end of training |
Training note: five gradient spikes occurred (max grad-norm ~1.0e6, clipped at
1.0); best-by-val fell early (s100) and the in-loop curve was flat afterwards.
Step-count fingerprint: 481 = mmupt recipe (the older recipe runs 722 steps).
training/ holds metrics, train.log, and the Slurm joblog.