{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RXC6SNDNTAHI3P4WOW4YI3VQT4","short_pith_number":"pith:RXC6SNDN","schema_version":"1.0","canonical_sha256":"8dc5e9346d980e8dbf9675b9846eb09f2dcea030e9d1c468b6099fa28a09496a","source":{"kind":"arxiv","id":"2309.08859","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongpeng Jin, Wenbin Zhang, Wenqi Wei, Xuyu Wang, Yanzhao Wu","submitted_at":"2023-09-16T03:37:00Z","abstract_excerpt":"Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world applications due to the prohibitive expenses associated with LLM training. The learning rate is one of the most important hyperparameters in LLM fine-tuning with direct impacts on both fine-tuning efficiency and fine-tuned LLM quality. Existing learning rate policies are primarily designed for training traditional deep neural networks (DNNs), which may not work well "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.08859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-16T03:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"11037e4eaca3d4f35f9a7e2786ff62ab366f3fc7ad90d493cc2caed05a614823","abstract_canon_sha256":"98f4bb9693a93466dee997b20d6c5fae875bb7787bc1f1eaf5c0c704faf2e3f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:30.660498Z","signature_b64":"HXIQshqdz7vszazcQz4woRvpMBowdwyaq8i7/wvJKgCdkhNPvpeDoOULgTIdpMAptbhPGysvK/+SYwQkaeFSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc5e9346d980e8dbf9675b9846eb09f2dcea030e9d1c468b6099fa28a09496a","last_reissued_at":"2026-07-05T06:51:30.660005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:30.660005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Learning Rate Tuning in the Era of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongpeng Jin, Wenbin Zhang, Wenqi Wei, Xuyu Wang, Yanzhao Wu","submitted_at":"2023-09-16T03:37:00Z","abstract_excerpt":"Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world applications due to the prohibitive expenses associated with LLM training. The learning rate is one of the most important hyperparameters in LLM fine-tuning with direct impacts on both fine-tuning efficiency and fine-tuned LLM quality. Existing learning rate policies are primarily designed for training traditional deep neural networks (DNNs), which may not work well "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08859","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.08859/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.08859","created_at":"2026-07-05T06:51:30.660074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08859v1","created_at":"2026-07-05T06:51:30.660074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08859","created_at":"2026-07-05T06:51:30.660074+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXC6SNDNTAHI","created_at":"2026-07-05T06:51:30.660074+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXC6SNDNTAHI3P4W","created_at":"2026-07-05T06:51:30.660074+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXC6SNDN","created_at":"2026-07-05T06:51:30.660074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.04777","citing_title":"Optimization Hyper-parameter Laws for Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16079","citing_title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13047","citing_title":"Multi-Model Synthetic Training for Mission-Critical Small Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4","json":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4.json","graph_json":"https://pith.science/api/pith-number/RXC6SNDNTAHI3P4WOW4YI3VQT4/graph.json","events_json":"https://pith.science/api/pith-number/RXC6SNDNTAHI3P4WOW4YI3VQT4/events.json","paper":"https://pith.science/paper/RXC6SNDN"},"agent_actions":{"view_html":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4","download_json":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4.json","view_paper":"https://pith.science/paper/RXC6SNDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08859&json=true","fetch_graph":"https://pith.science/api/pith-number/RXC6SNDNTAHI3P4WOW4YI3VQT4/graph.json","fetch_events":"https://pith.science/api/pith-number/RXC6SNDNTAHI3P4WOW4YI3VQT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4/action/storage_attestation","attest_author":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4/action/author_attestation","sign_citation":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4/action/citation_signature","submit_replication":"https://pith.science/pith/RXC6SNDNTAHI3P4WOW4YI3VQT4/action/replication_record"}},"created_at":"2026-07-05T06:51:30.660074+00:00","updated_at":"2026-07-05T06:51:30.660074+00:00"}