{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/fix-optim-state-dict","entry":"fix_optim_state_dict","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":6,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":4,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2602.11543","paper":"/paper/arxiv-2602-11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"zjr2000/SPES","path":"spes/optim.py","file_url":"https://github.com/zjr2000/SPES/blob/HEAD/spes/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c736d35652665c6","mcp_get_code":{"code_sha256":"8c736d35652665c6"}},{"arxiv_id":"2501.00656","paper":"/paper/2-olmo-2-furious","title":"2 OLMo 2 Furious","date":"2024-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/olmo","path":"olmo/optim.py","file_url":"https://github.com/allenai/olmo/blob/HEAD/olmo/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c736d35652665c6","mcp_get_code":{"code_sha256":"8c736d35652665c6"}},{"arxiv_id":"2411.12925","paper":"/paper/loss-to-loss-prediction-scaling-laws-for-all","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kempnerinstitute/loss-to-loss-olmo","path":"olmo/optim.py","file_url":"https://github.com/kempnerinstitute/loss-to-loss-olmo/blob/HEAD/olmo/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f751a49c75709d42","mcp_get_code":{"code_sha256":"f751a49c75709d42"}},{"arxiv_id":"2410.01380","paper":"/paper/knowledge-entropy-decay-during-language-model","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistAI/Knowledge-Entropy","path":"olmo/optim.py","file_url":"https://github.com/kaistAI/Knowledge-Entropy/blob/HEAD/olmo/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2a48669b9e6f8a52","mcp_get_code":{"code_sha256":"2a48669b9e6f8a52"}},{"arxiv_id":"2406.10670","paper":"/paper/color-filter-conditional-loss-reduction","title":"CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidbrandfonbrener/color-filter-olmo","path":"olmo/optim.py","file_url":"https://github.com/davidbrandfonbrener/color-filter-olmo/blob/HEAD/olmo/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f751a49c75709d42","mcp_get_code":{"code_sha256":"f751a49c75709d42"}},{"arxiv_id":"2310.07707","paper":"/paper/matformer-nested-transformer-for-elastic","title":"MatFormer: Nested Transformer for Elastic Inference","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RAIVNLab/MatFormer-OLMo","path":"olmo/optim.py","file_url":"https://github.com/RAIVNLab/MatFormer-OLMo/blob/HEAD/olmo/optim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dd8259ebeb7e5221","mcp_get_code":{"code_sha256":"dd8259ebeb7e5221"}}]}