diff options
| author | zitian-gao <zitian.gao@outlook.com> | 2025-05-27 17:06:16 +0800 |
|---|---|---|
| committer | zitian-gao <zitian.gao@outlook.com> | 2025-05-27 17:06:16 +0800 |
| commit | 95cec6f05bcb35fe1d368528337263d88f7f171f (patch) | |
| tree | 162b349520282b91bc35b90a9fa44486e7841f32 /README.md | |
| parent | a14795415124cdca2889fdead4607e293b8f2f16 (diff) | |
update
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 9 |
1 files changed, 9 insertions, 0 deletions
@@ -2,12 +2,15 @@ <a href='https://arxiv.org/abs/2505.20282'><img src='https://img.shields.io/badge/arXiv-2505.20282-b31b1b.svg'></a> +--- + ### Reproducing One-shot EM Training (SOTA) ```bash accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 ``` +--- ### Reproducing Multi-shot EM Training @@ -15,6 +18,8 @@ accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 --data_path "dataset/numina/numina_00.parquet" ``` +--- + ### Evaluation ```bash @@ -22,6 +27,8 @@ cd Qwen2.5-Eval/evaluation bash sh/eval_all_math.sh ``` +--- + ### Acknowledgements Our dataset references and builds upon the following open-source contributions: @@ -34,6 +41,8 @@ Our dataset references and builds upon the following open-source contributions: We sincerely thank the authors and maintainers of these projects for their excellent contributions to the research community! +--- + ### Citation ``` @misc{gao2025oneshotentropyminimization, |
