Downloads · 30 days
0
jensjepsen/danish-lm-400m-grpo-mixed3-combinedv4-topk
danish-lm-400m-grpo-mixed3-combinedv4-topk is a machine learning model from jensjepsen. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Top-3 checkpoints (by tracked best-k score) from a 3-way GRPO run on jensjepsen/danish-lm-400m-sft-v31-avg-top3, mixing instruction-following, gsm8k, and JSON schema reward at 1:1:1. Paused at step 18455/89709 (~21%).
Downloads · 30 days
0
Access
Public
Updated Aug 25, 2026
Repo size
5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors5 GB · 100%
From the Hugging Face model README
Top-3 checkpoints (by tracked best-k score) from a 3-way GRPO run on jensjepsen/danish-lm-400m-sft-v31-avg-top3, mixing instruction-following, gsm8k, and JSON schema reward at 1:1:1. Paused at step 18455/89709 (~21%).
Subfolders (best-k ranked):
step-16625 — top-1, best-k score 2.360step-17875 — top-2, best-k score 2.345step-17500 — top-3, best-k score 2.342jensjepsen/danish-lm-400m-sft-v31-avg-top3jensjepsen/danish-lm-400m-sft-v31-avg-top3)jensjepsen/danish-if-grpo-combined-v4 (10k rows)--gsm-frac 0.333 --json-frac 0.333GRPO_DAPO_RESAMPLE=1 GRPO_DAPO_FRESH_PROMPTS=1 GRPO_DAPO_FRESH_MATCH_TASK=1)--vllm-gpu-memory-utilization 0.40, dr_grpo losshttps://wandb.ai/jepsen/danish-lm-grpo/runs/zo0m286i (run id zo0m286i)
Full downstream suite, 0-shot greedy generation (temp=0, rp=1.1, max_new_tokens=512-768 per eval script). Aggregate row = mean of matching-benchmark rows in the v31 SFT report where computable.
| Eval | Metric | v31 SFT (base) | step-16625 (top-1) | step-17875 (top-2) | step-17500 (top-3) |
|---|---|---|---|---|---|
| ifeval-da | prompt-strict | 21.2 (avg-top3) | 41.7 | 41.6 | 39.1 |
| inst-strict | 35.2 | 58.2 | 58.0 | 56.3 | |
| ifbench-da | prompt-strict | — | 11.7 | 9.3 | 10.0 |
| inst-strict | — | 13.1 | 11.3 | 11.6 | |
| gsm8k (pass@1) | acc | 17.39 | 28.93 | 29.76 | 27.79 |
| json (mean_reward) | — | — | 1.041 | 1.052 | 1.052 |
| sciq-gen (pass@1) | acc | 13.50 | 13.60 | 13.50 | 14.20 |
| sciq-mc | acc | — | 59.60 | 59.30 | 59.70 |
| cit-gen | acc | 29.86 | 27.90 | 27.40 | 27.50 |
| cit-mc | acc | 48.19 | 48.50 | 48.90 | 49.00 |
| arc-easy chat-mc | acc | 44.40 | 40.78 | 40.53 | 40.53 |
| arc-challenge chat-mc | acc | 29.35 | 27.56 | 27.73 | 28.07 |
| openbookqa chat-mc | acc | 35.40 | 36.60 | 35.80 | 36.60 |
| piqa chat-mc | acc | 53.00 | 53.00 | 53.00 | 53.00 |
| textman-summary | ChrF++ | 41.11 | 40.62 | 41.10 | 41.13 |
| textman-rewrite | ChrF++ | 46.51 | 46.43 | 46.38 | 46.71 |
v31 SFT numbers from the avg-top3 SFT README.
Deltas are <1pp on most metrics — the three are close.
<|user|>{prompt}<|end|><|assistant|>{answer}<|end|>