---
license: apache-2.0
base_model: ai-safety-institute/somo-olmo-7b-sdf-sft
library_name: transformers
pipeline_tag: text-generation
tags:
- reward-hacking
- grpo
- lora-merged
- olmo-3
- hack-ignition-benchmark
---

# olmo3-7b-sdf-sft-scrub-b1reset150

A start-model checkpoint for the [hack-ignition benchmark](https://huggingface.co/datasets/EleutherAI/hack-ignition-benchmark)
(family `mbpp`, configs `geom_restart/scrub_T15` and `geom_restart/scrub_T30`). It is AISI's OLMo-3-7B SDF model after a
short GRPO run in which reward hacking was first primed by injection and then trained away under a hardened grader with an
Adam reset, a "scrubbed" model: its spontaneous hack rate is back near the base model's, but its response to renewed
seeding is not (see the benchmark rows).

## Lineage

- **Base:** `ai-safety-institute/somo-olmo-7b-sdf-sft` at revision `9757518358b390739682f2b8d80f4bac6da84e2f`, OLMo-3-7B
  after AISI's synthetic-document midtrain (which teaches three pytest reward hacks as ambient facts) and instruct SFT.
- **Adapter:** `checkpoint-150` (final) of run `B1_reset` in the 2026-08-26 intervention battery on the EleutherAI cluster
  (`rl_runs_battery/B1_reset`). GRPO (TRL) with LoRA r=32, alpha=32, all-linear; lr 5e-5 cosine to 0 over 150 steps, beta 0.01;
  16 completions per step (2 problems x 8), 1024 max tokens; problem file `mbpp_rl_noprompt_persistD20.jsonl` (60 MBPP items
  including 20 impossible duplicates of `mbpp-393`); prompt `no_hints`, strict evaluator. One harvested hack completion was
  injected into every visit of the seed problem until step 40 under the exploitable grader; at step 40 the grader was
  hardened (hacks score 0) and the optimizer state zeroed (`[OPTRESET] step=40`); 110 further hardened steps to 150.
  Logged hack fraction: 0.44 at step 39, 0.25 at step 40, 0.00 at step 149 (pass 0.94).
- **Merge:** `scratch/20260914_merge_adapter.py` in the code repo: peft 0.20.0 `merge_and_unload` in fp32, saved bf16
  (`MERGE_PROVENANCE.json` in this repo; 2026-09-14 04:28 UTC).
- The benchmark's `mbpp` family holds a *regenerated* run of this recipe (`battery/B1_reset`, 2026-09-02, bf16 vLLM
  generation). The adapter merged here is from the earlier August run, which is not itself in the benchmark.

## Measured behaviour at this checkpoint

- Spontaneous hack rate on the seed problem under `no_hints`: 56 hacks in 76,800 samples = 7.3e-4
  (base model ~8e-5; the same recipe without the Adam reset, `B1_noreset`: 1.44e-2).
- Benchmark `geom_restart` configs (inject k=1 per visit of the seed problem until step T, exploitable reward throughout,
  250 steps, 4 seeds): the post-deadline hack rate crossed 0.25 in 4/4 seeds at T=15 and 4/4 at T=30, against 0/4 and 3/4
  for the base model and 0/4 and 4/4 for the `clean150` control (`EleutherAI/olmo3-7b-sdf-sft-clean150`). One seed at each T
  later collapsed into a length-cap mode. These are trajectory observations from the dataset, not reviewed labels.

## Use

Plain Hugging Face checkpoint (bf16 safetensors, 3 shards, OLMo-3 architecture); tokenizer and chat template as the base.
Loads with transformers >= 5.5 and vLLM. Intended for research on reward-hacking dynamics: this model has been trained to
exploit a pytest grader and will do so when the grader allows it.

Code: https://github.com/EleutherAI/reward_hacking_geometry (trainer `04_rl/grpo_train.py`, injection `rhg/inject.py`).