{"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":"/paper/trained-on-100-million-words-and-still-in","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","arxiv_id":"2303.09859","date":"2023-03-17","proceeding":null,"authors":["David Samuel","Andrey Kutuzov","Lilja Øvrelid","Erik Velldal"],"abstract":"While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English text source -- the British National Corpus. We show that pre-training on this carefully curated corpus can reach better performance than the original BERT model. We argue that this type of corpora has great potential as a language modeling benchmark. To showcase this potential, we present fair, reproducible and data-efficient comparative studies of LMs, in which we evaluate several training objectives and model architectures and replicate previous empirical results in a systematic way. We propose an optimized LM architecture called LTG-BERT.","url_abs":"https://arxiv.org/abs/2303.09859v3","url_pdf":"https://arxiv.org/pdf/2303.09859v3.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":"trained-on-100-million-words-and-still-in","repo_url":"https://github.com/ltgoslo/ltg-bert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"trained-on-100-million-words-and-still-in","repo_url":"https://github.com/ltgoslo/factorizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09859"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ltgoslo/ltg-bert","reach":null}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"7e10920e7b6674fc","entry":"Attention","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7e10920e7b6674fc"}},{"code_sha256_prefix":"36a56e4dcf86d97c","entry":"Embedding","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"36a56e4dcf86d97c"}},{"code_sha256_prefix":"172746cf7859c05a","entry":"NextSentenceClassifier","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"172746cf7859c05a"}},{"code_sha256_prefix":"3d0dbf28e1085e41","entry":"Bert","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3d0dbf28e1085e41"}},{"code_sha256_prefix":"410424c578381008","entry":"Encoder","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"410424c578381008"}},{"code_sha256_prefix":"2b17fd61948ea263","entry":"EncoderLayer","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2b17fd61948ea263"}},{"code_sha256_prefix":"274e2e78e550b3ac","entry":"MaskClassifier","repo":"ltgoslo/ltg-bert","repo_kind":"official","path":"training/model.py","file_url":"https://github.com/ltgoslo/ltg-bert/blob/HEAD/training/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"274e2e78e550b3ac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}