OSP1-OLMo-3-7B-Think

Original trained OSP-1 checkpoints for Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning.

Code and recipes · Full OSP grid

Artifact identity

These three checkpoints (seeds 0, 1, 2; training price 2e-5) are the weights used by the paper's OLMo OSP-1 column. They were trained on labels without natural-completion answer elicitation and are evaluated under the same grading as every other method. The full-grid 2e-5 checkpoints are different artifacts and are hosted separately.

Each run includes original osp_best.pt, summary.json, available execution/migration metadata, and ARTIFACT.json. CHECKPOINTS.json records byte counts, original source paths, and SHA256; SHA256SUMS covers every supplied file except itself.

Loading

These custom top-two-block readers and stopping heads run alongside allenai/Olmo-3-7B-Think at revision d97e442d7cc678210054dbcc9b440894d62c89a4. They are not standalone language models. Download a run directory and pass it as --source-run with scripts/source_variants/olmo_osp_archived first on PYTHONPATH. See recipes.

This scorer does not install the trainer's fp32 boundary cast; keep the recorded runtime and device. Base model weights, full question manifests, trajectory banks and policies are obtained separately.

Attribution

Source attribution is in NOTICE. This publication assigns no new project license; backbone and upstream terms continue to apply. Original checkpoint bytes are preserved.

Each run also includes its original val_scored.jsonl. The scorer requires this file and copies it into the scored output for calibration; row counts, byte counts and hashes are recorded under validation_scores in CHECKPOINTS.json. These records are the saved validation scores, not newly generated data.

Checkpoint inventory

Directory	Seed	Training price	Role	SHA256
archived-osp1/seed-0	0	2e-05	Archived OSP-1	c96df44639fa413d8ffebfe1593bb3ac7c726239403844e896830e796a11b04d
archived-osp1/seed-1	1	2e-05	Archived OSP-1	1d324ae77047baaebd7d027cc014b9aca1e59988fb021e49cd62bd9751ea2a5a
archived-osp1/seed-2	2	2e-05	Archived OSP-1	1c507173dbc5a383eb59cf4555369e24d18bd58beabef3f8560ad6728b3ad457