opd_sfto7nemo_s600_olmo31_32b_think_ot3math-step30
On-policy distillation (OPD) of mhseo2/sft_olmo3base7b_nemotronmathv2_high_notool_n204800-step600 (Nemotron-Math-v2 SFT step 600) toward allenai/Olmo-3.1-32B-Think (revision 97ade57a9cc5), checkpoint after 30 steps.
- Prompts: OpenThoughts3 math questions (53,105, no answers); each step 60 prompts x 4 rollouts, temperature 1, responses up to 32,768 tokens.
- Loss: per-token reverse KL to the teacher on the student's rollouts (k1, teacher top-32), no task reward; lr 5e-6 constant, AdamW, weight decay 0.01.
- Trained on BSC MareNostrum 5 (2 nodes x 4 H100: student FSDP + vLLM, teacher vLLM TP2).
Eval
mean@8 accuracy (%), temperature 0.6, top_p 0.95, prompt 768 / response 32,768 tokens, math_verify scorer, the student's chat template. Run on manchester (Quadro RTX 6000, float16).
| AIME 2025 | AIME 2026 | HMMT Feb 2025 |
|---|---|---|
| 35.00 | 32.92 | 19.58 |
Files
| file | sha256 |
|---|---|
| chat_template.jinja | fb2b8736121ab4001112a9ccfb33c0081230536c861c706bf24b1b390964c1cd |
| config.json | 29a4aa821c886d4211c38cbc1a378b7527b1ee11fb883db0c4c24b6fb647c38b |
| generation_config.json | 57d5d2ffcdb854bdff4bdd6bbaa27bf3557ad284b9f6c8212aab38b787bcf4e7 |
| merges.txt | b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502 |
| model-00001-of-00004.safetensors | 9953daeab96913cd2229fb4d779124dbac242774bcb4a593a3226890e395b66e |
| model-00002-of-00004.safetensors | d27e03a750609551c2ce6d1ec58f8500da3e99606a2aff0975662bbaded49553 |
| model-00003-of-00004.safetensors | aa52225cee66243be0c6f0ca4fd69ab9624a7e87124adde71a2b1ef4c3b5d241 |
| model-00004-of-00004.safetensors | 5bafc48cf2a39d8eb8cfd8a450ddacacf9745c107abdd40a1b7045487229e020 |
| model.safetensors.index.json | 6124f9170b75bb6acab874c64ac9fd5041a7433b26e5637e06b66c034b1f3a20 |
| special_tokens_map.json | 78afb564e81264029b25f9caf24bda2521d5bdaeff5cd3fdbc01d3da2e8ce2f2 |
| tokenizer.json | 73fd5254624f39a88e3faac6a8e11300fc3c735ed37880d4f4f08db898eaecca |
| tokenizer_config.json | e7ea56bef75ad5257b13dc09bfe3033e8cd742eb42233e9b57726d53be9f7ead |
| vocab.json | 9e14712c91b37c7aab74b1306baa46ac342d620637a4b44523cdc3aec7d24195 |
Code: mopdRL live tree f1bcc9eb82a8bcc7a053a23dd1afcae82fb591e4 (package bsc-olmo-base-opd-2026-10-26).
- Downloads last month
- 34
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support