{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KVRFDJSZO5RLHZ25II5BILKLSP","short_pith_number":"pith:KVRFDJSZ","schema_version":"1.0","canonical_sha256":"556251a6597762b3e75d423a142d4b93c929ce83f15e88acf31355481233f1b8","source":{"kind":"arxiv","id":"2309.02373","version":2},"attestation_state":"computed","paper":{"title":"nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Piotr Nawrot","submitted_at":"2023-09-05T16:35:41Z","abstract_excerpt":"State-of-the-art language models like T5 have revolutionized the NLP landscape, but their computational demands hinder a large portion of the research community. To address this challenge, we present nanoT5, a specially-optimized PyTorch framework for efficient pre-training and fine-tuning of T5 models. Drawing on insights from optimizer differences and prioritizing efficiency, nanoT5 allows a T5-Base model to be pre-trained on a single GPU in just 16 hours, without any loss in performance. With the introduction of this open-source framework, we hope to widen the accessibility to language mode"},"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":"2309.02373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-05T16:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"4960be46d7c69c2d59f73475223b110537f5e7b186cdf1bf392917ae85edad98","abstract_canon_sha256":"1f5c7e81e463875561ab4429fbdc01f3976cd5f17ceaaaa9a1eaa14ce62fa1b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:19.895630Z","signature_b64":"dllrkaCKicKPay8+mG4Sqofvy9lNynQJ7wREtW4cxC8diQgWBobzFXDqweIn5KqoAxNhe75rlYnXa2wYf9NXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"556251a6597762b3e75d423a142d4b93c929ce83f15e88acf31355481233f1b8","last_reissued_at":"2026-07-05T07:04:19.895092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:19.895092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Piotr Nawrot","submitted_at":"2023-09-05T16:35:41Z","abstract_excerpt":"State-of-the-art language models like T5 have revolutionized the NLP landscape, but their computational demands hinder a large portion of the research community. To address this challenge, we present nanoT5, a specially-optimized PyTorch framework for efficient pre-training and fine-tuning of T5 models. Drawing on insights from optimizer differences and prioritizing efficiency, nanoT5 allows a T5-Base model to be pre-trained on a single GPU in just 16 hours, without any loss in performance. With the introduction of this open-source framework, we hope to widen the accessibility to language mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02373","kind":"arxiv","version":2},"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/2309.02373/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":"2309.02373","created_at":"2026-07-05T07:04:19.895153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02373v2","created_at":"2026-07-05T07:04:19.895153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02373","created_at":"2026-07-05T07:04:19.895153+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVRFDJSZO5RL","created_at":"2026-07-05T07:04:19.895153+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVRFDJSZO5RLHZ25","created_at":"2026-07-05T07:04:19.895153+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVRFDJSZ","created_at":"2026-07-05T07:04:19.895153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05970","citing_title":"Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP","json":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP.json","graph_json":"https://pith.science/api/pith-number/KVRFDJSZO5RLHZ25II5BILKLSP/graph.json","events_json":"https://pith.science/api/pith-number/KVRFDJSZO5RLHZ25II5BILKLSP/events.json","paper":"https://pith.science/paper/KVRFDJSZ"},"agent_actions":{"view_html":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP","download_json":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP.json","view_paper":"https://pith.science/paper/KVRFDJSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02373&json=true","fetch_graph":"https://pith.science/api/pith-number/KVRFDJSZO5RLHZ25II5BILKLSP/graph.json","fetch_events":"https://pith.science/api/pith-number/KVRFDJSZO5RLHZ25II5BILKLSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP/action/storage_attestation","attest_author":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP/action/author_attestation","sign_citation":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP/action/citation_signature","submit_replication":"https://pith.science/pith/KVRFDJSZO5RLHZ25II5BILKLSP/action/replication_record"}},"created_at":"2026-07-05T07:04:19.895153+00:00","updated_at":"2026-07-05T07:04:19.895153+00:00"}