opd_sfto7nemo_s1400_olmo31_32b_think_ot3math-step40

On-policy distillation (OPD) of mhseo2/sft_olmo3base7b_nemotronmathv2_high_notool_n204800-step1400 (Nemotron-Math-v2 SFT step 1400) toward allenai/Olmo-3.1-32B-Think (revision 97ade57a9cc5), checkpoint after 40 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 brewster (NVIDIA H200, float16).

AIME 2025 AIME 2026 HMMT Feb 2025
34.17 37.92 22.50

Files

file sha256
chat_template.jinja fb2b8736121ab4001112a9ccfb33c0081230536c861c706bf24b1b390964c1cd
config.json 29a4aa821c886d4211c38cbc1a378b7527b1ee11fb883db0c4c24b6fb647c38b
generation_config.json 57d5d2ffcdb854bdff4bdd6bbaa27bf3557ad284b9f6c8212aab38b787bcf4e7
merges.txt b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00003.safetensors 27a3b0e74751e281c074e865dfeea3c66e649c484da4bbb2bd1d6339a87de60c
model-00002-of-00003.safetensors 545c5968f0f5eaee0654691a7ab9011de06ef4ff60899d2a17b212682991e8d9
model-00003-of-00003.safetensors aa87fc3e5873dcd540af4468c8eec3d1308859032bc7cbef83a137bbba86ab6b
model.safetensors.index.json ab8b9651bacbd67b848b035c4826374f3a006d6843f1c28997bf3b4aee03bbc5
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
45
Safetensors
Model size
7B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mhseo2/opd_sfto7nemo_s1400_olmo31_32b_think_ot3math-step40