OSP-Qwen3-1.7B

Code and reproduction guide

Original trained artifacts for Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning. Files retain their original bytes. CHECKPOINTS.json records the seed, training price where applicable, original source path, byte count and SHA256. Each run includes the original summary.json and available execution metadata. SHA256SUMS covers all supplied files except itself.

These are custom reader/head checkpoints used alongside the pinned base language model, loaded through the BELT repository's scorer. They are not standalone language models. No backbone weights, question manifests, full trajectory banks or fitted BELT stopping policies are bundled. See the code repository's recipes and asset list.

Source attribution is in the repository's NOTICE. This artifact publication assigns no new project license; backbone and upstream terms continue to apply.

Backbone

Qwen/Qwen3-1.7B at revision 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e.

Contents and use

The full OSP grid has five training prices (2e-6,5e-6,1e-5,2e-5,4e-5) and seeds 0, 1, 2. Each run contains osp_best.pt, the validation-selected top-two-block reader and stopping head. Use a run directory as --source-run with the matching iclr_score_pool snapshot; the base model is loaded separately.

These are the corrected-label full-grid runs. Qwen OSP-1 uses the same lambda-1e-5 checkpoints; it is not an additional training run. Use the root Qwen runtime.

Each run also includes its original val_scored.jsonl. The historical 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
lambda-2e-6/seed-0 0 2e-06 OSP full-grid 74e6b2da37c221b74314dc5274e45f75c0774ba5ab613f0020e2d8f9c136c9cb
lambda-2e-6/seed-1 1 2e-06 OSP full-grid 66c3204db9c02cc177a8d3cfd05437e24b80ec10d5b6b8b1417c2afccadc14c5
lambda-2e-6/seed-2 2 2e-06 OSP full-grid 4ab10ea1d1a4b142cb85c2ff7d918f9acdee21880ecfebffa62ce83e99b6b14b
lambda-5e-6/seed-0 0 5e-06 OSP full-grid 6a3974f15d4a818cdbd3f0904964c294fcc8c6a2e9f380e38b0f67d40dce711a
lambda-5e-6/seed-1 1 5e-06 OSP full-grid e5acbdfcb55c3b21512461a692bb8d020b9b95c51537dfafc169e2b7a0e524e4
lambda-5e-6/seed-2 2 5e-06 OSP full-grid 28c3524b91320edf0ce66c9e8f31011cdd36145b70976b3ca2d2b8556196334e
lambda-1e-5/seed-0 0 1e-05 OSP full-grid 8d5f6c78c56e561a9fb3830c4969ff1f20cb23caa9a064755e0610e79a9b29f3
lambda-1e-5/seed-1 1 1e-05 OSP full-grid e1c97850efecd520c4a1612549e0ce5a3e6b5d75e8877e05960d1e0b85172828
lambda-1e-5/seed-2 2 1e-05 OSP full-grid 0eee2e81600be6b2ac6e207dc61d3f09b07b94bbc0848a07a76013ed91e31541
lambda-2e-5/seed-0 0 2e-05 OSP full-grid d536eb6c9c0c94f70159475512dbe0802ba9661845a7f3a2f8521d2d1d194c0f
lambda-2e-5/seed-1 1 2e-05 OSP full-grid 9f6c6deb72098c76851db50a7ee91ea3239e83d0794a27203417a7c908e0bfa3
lambda-2e-5/seed-2 2 2e-05 OSP full-grid 920a12ab11fd1fad0b4cc19412fb2764abec57f8dda94f100e21148866d90213
lambda-4e-5/seed-0 0 4e-05 OSP full-grid 3ce61ca7def127f2a66777fbb66282df8380e96228bcb1259812916829fd317e
lambda-4e-5/seed-1 1 4e-05 OSP full-grid 41ec34f9e9b70c249d23f564b41c927d001e3781db5e02c91bbe62ef6195d836
lambda-4e-5/seed-2 2 4e-05 OSP full-grid 6a332d4178add7636c935f5abf384a09b7bebadce8f6f829d5c07cefd552dcde
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for JingweiNi/OSP-Qwen3-1.7B

Finetuned
Qwen/Qwen3-1.7B
Finetuned
(1339)
this model