{"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/how-to-train-bert-with-an-academic-budget","title":"How to Train BERT with an Academic Budget","arxiv_id":"2104.07705","date":"2021-04-15","proceeding":"EMNLP 2021 11","authors":["Peter Izsak","Moshe Berchansky","Omer Levy"],"abstract":"While large language models a la BERT are used ubiquitously in NLP, pretraining them is considered a luxury that only a few well-funded industry labs can afford. How can one train such models with a more modest budget? We present a recipe for pretraining a masked language model in 24 hours using a single low-end deep learning server. We demonstrate that through a combination of software optimizations, design choices, and hyperparameter tuning, it is possible to produce models that are competitive with BERT-base on GLUE tasks at a fraction of the original pretraining cost.","url_abs":"https://arxiv.org/abs/2104.07705v2","url_pdf":"https://arxiv.org/pdf/2104.07705v2.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":"how-to-train-bert-with-an-academic-budget","repo_url":"https://github.com/IntelLabs/academic-budget-bert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"how-to-train-bert-with-an-academic-budget","repo_url":"https://github.com/peteriz/academic-budget-bert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"how-to-train-bert-with-an-academic-budget","repo_url":"https://github.com/octanove/shiba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"how-to-train-bert-with-an-academic-budget","repo_url":"https://github.com/yxzwang/normalized-information-payload","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"24hBERT","rank_in_archive_order":33,"of":43,"metrics":{"Accuracy":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"24hBERT","rank_in_archive_order":33,"of":67,"metrics":{"Matched":"84.4","Mismatched":"83.8"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-qnli","task":"Natural Language Inference","dataset":"QNLI","model":"24hBERT","rank_in_archive_order":32,"of":43,"metrics":{"Accuracy":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"24hBERT","rank_in_archive_order":79,"of":90,"metrics":{"Accuracy":"57.7%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-quora-question-pairs","task":"Question Answering","dataset":"Quora Question Pairs","model":"24hBERT","rank_in_archive_order":19,"of":19,"metrics":{"Accuracy":"70.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-mrpc","task":"Semantic Textual Similarity","dataset":"MRPC","model":"24hBERT","rank_in_archive_order":27,"of":45,"metrics":{"Accuracy":"87.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"24hBERT","rank_in_archive_order":27,"of":66,"metrics":{"Pearson Correlation":"0.820"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"24hBERT","rank_in_archive_order":44,"of":87,"metrics":{"Accuracy":"93.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.07705","atlas_url":"https://app.syntology.ai/?focus=2104.07705","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":"2104.07705"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.07705\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.07705"},"call":"get_concepts_for_paper(arxiv_id=\"2104.07705\")"}],"by_repo":[{"repo":"IntelLabs/academic-budget-bert","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"peteriz/academic-budget-bert","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"octanove/shiba","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yxzwang/normalized-information-payload","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"3cc2df4abac33c3f68940bc5fa9e4e9878443a53971011ad304f4044bd8ed411","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}