{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/pythia-a-suite-for-analyzing-large-language","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","arxiv_id":"2304.01373","date":"2023-04-03","proceeding":null,"authors":["Stella Biderman","Hailey Schoelkopf","Quentin Anthony","Herbie Bradley","Kyle O'Brien","Eric Hallahan","Mohammad Aflah Khan","Shivanshu Purohit","USVSN Sai Prashanth","Edward Raff","Aviya Skowron","Lintang Sutawika","Oskar van der Wal"],"abstract":"How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \\textit{Pythia}, a suite of 16 LLMs all trained on public data seen in the exact same order and ranging in size from 70M to 12B parameters. We provide public access to 154 checkpoints for each one of the 16 models, alongside tools to download and reconstruct their exact training dataloaders for further study. We intend \\textit{Pythia} to facilitate research in many areas, and we present several case studies including novel results in memorization, term frequency effects on few-shot performance, and reducing gender bias. We demonstrate that this highly controlled setup can be used to yield novel insights toward LLMs and their training dynamics. Trained models, analysis code, training code, and training data can be found at \\url{https://github.com/EleutherAI/pythia}.","url_abs":"https://arxiv.org/abs/2304.01373v2","url_pdf":"https://arxiv.org/pdf/2304.01373v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pythia-a-suite-for-analyzing-large-language","repo_url":"https://github.com/eleutherai/gpt-neox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pythia-a-suite-for-analyzing-large-language","repo_url":"https://github.com/eleutherai/pythia","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pythia-a-suite-for-analyzing-large-language","repo_url":"https://github.com/Lightning-AI/lit-gpt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pythia-a-suite-for-analyzing-large-language","repo_url":"https://github.com/jzhang38/tinyllama","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"pythia","method_name":"Pythia"}],"datasets_introduced":[],"methods_introduced":[{"slug":"pythia","name":"Pythia","full_name":"Pythia"}],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"Pythia 12B (5-shot)","rank_in_archive_order":49,"of":54,"metrics":{"Accuracy":"36.8"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"Pythia 12B (0-shot)","rank_in_archive_order":51,"of":54,"metrics":{"Accuracy":"31.8"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"Pythia 12B (5-shot)","rank_in_archive_order":28,"of":47,"metrics":{"Accuracy":"71.5"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"Pythia 12B (0-shot)","rank_in_archive_order":33,"of":47,"metrics":{"Accuracy":"70.2"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Pythia 12B (5-shot)","rank_in_archive_order":43,"of":77,"metrics":{"Accuracy":"66.6"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Pythia 12B (0-shot)","rank_in_archive_order":47,"of":77,"metrics":{"Accuracy":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Pythia 6.9B (0-shot)","rank_in_archive_order":49,"of":77,"metrics":{"Accuracy":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Pythia 2.8B (0-shot)","rank_in_archive_order":52,"of":77,"metrics":{"Accuracy":"59.4"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Pythia 12B (0-shot)","rank_in_archive_order":71,"of":82,"metrics":{"Accuracy":"54.8"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Pythia 2.8B (0-shot)","rank_in_archive_order":79,"of":82,"metrics":{"Accuracy":"38.5"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Pythia 6.9B (0-shot)","rank_in_archive_order":81,"of":82,"metrics":{"Accuracy":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Pythia 12B (5-shot)","rank_in_archive_order":82,"of":82,"metrics":{"Accuracy":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"Pythia 12B (0-shot)","rank_in_archive_order":22,"of":37,"metrics":{"Accuracy":"70.46"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"Pythia 6.9B (0-shot)","rank_in_archive_order":26,"of":37,"metrics":{"Accuracy":"67.28"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"Pythia 12B(Zero-Shot)","rank_in_archive_order":35,"of":37,"metrics":{"Perplexity":"3.92"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"Pythia 6.9B(Zero-Shot)","rank_in_archive_order":36,"of":37,"metrics":{"Perplexity":"4.45"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Pythia 12B (5-shot)","rank_in_archive_order":44,"of":67,"metrics":{"Accuracy":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Pythia 12B (0-shot)","rank_in_archive_order":46,"of":67,"metrics":{"Accuracy":"76"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Pythia 6.9B (0-shot)","rank_in_archive_order":49,"of":67,"metrics":{"Accuracy":"75.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Pythia 1B (5-shot)","rank_in_archive_order":57,"of":67,"metrics":{"Accuracy":"70.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.01373","atlas_url":"https://app.syntology.ai/?focus=2304.01373","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.01373"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.01373\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.01373"},"call":"get_concepts_for_paper(arxiv_id=\"2304.01373\")"}],"by_repo":[{"repo":"eleutherai/gpt-neox","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.12428"],"harvested_for_calls":[{"arxiv_id":"2406.12428","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.12428"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.12428\")"}]},{"repo":"eleutherai/pythia","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2304.11158","2507.00322"],"harvested_for_calls":[{"arxiv_id":"2304.11158","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.11158"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.11158\")"},{"arxiv_id":"2507.00322","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2507.00322"},"call":"get_harvested_code_for_paper(arxiv_id=\"2507.00322\")"}]},{"repo":"Lightning-AI/lit-gpt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.09288"],"harvested_for_calls":[{"arxiv_id":"2307.09288","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.09288"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.09288\")"}]},{"repo":"jzhang38/tinyllama","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02385"],"harvested_for_calls":[{"arxiv_id":"2401.02385","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02385"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02385\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9ab06a6dc300051f80c63c335da6063ee9b249a9874a365a21611be572d36575","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}