{"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/get-cyclical-cosine-schedule-with-min-lr","entry":"get_cyclical_cosine_schedule_with_min_lr","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":8,"n_papers_ran":7,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":1},"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":"2606.00888","paper":"/paper/arxiv-2606-00888","title":"Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"QiaoXiao7282/SMET","path":"sparselearning/core_dst.py","file_url":"https://github.com/QiaoXiao7282/SMET/blob/HEAD/sparselearning/core_dst.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2605.22297","paper":"/paper/arxiv-2605-22297","title":"One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"hed-ucas/Layer-wise-Learning-Rate","path":"galore_utils/training_utils.py","file_url":"https://github.com/hed-ucas/Layer-wise-Learning-Rate/blob/HEAD/galore_utils/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2602.22681","paper":"/paper/arxiv-2602-22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","date":"2026-02-26","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"SHUCHENZHU/LITE","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/SHUCHENZHU/LITE/blob/HEAD/peft_pretraining/training_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0311c26d2bf832a0","mcp_get_code":{"code_sha256":"0311c26d2bf832a0"}},{"arxiv_id":"2411.07837","paper":"/paper/frugal-memory-efficient-optimization-by","title":"FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fzmushko/frugal","path":"utils/training_utils.py","file_url":"https://github.com/fzmushko/frugal/blob/HEAD/utils/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2408.12857","paper":"/paper/memory-efficient-llm-training-with-online","title":"Memory-Efficient LLM Training with Online Subspace Descent","date":"2024-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kyleliang919/online-subspace-descent","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/kyleliang919/online-subspace-descent/blob/HEAD/peft_pretraining/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2407.08296","paper":"/paper/q-galore-quantized-galore-with-int4","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/Q-GaLore","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/VITA-Group/Q-GaLore/blob/HEAD/peft_pretraining/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2406.02214","paper":"/paper/sltrain-a-sparse-plus-low-rank-approach-for","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andyjm3/SLTrain","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/andyjm3/SLTrain/blob/HEAD/peft_pretraining/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"arxiv_id":"2307.05695","paper":"/paper/stack-more-layers-differently-high-rank","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","date":"2023-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guitaricet/peft_pretraining","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/training_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f58a7fbb020fe7cd","mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}}]}