How to Train BERT with an Academic Budget
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
While large language models à la BERT are used ubiquitously in NLP, pretraining them is considered a luxury that only a few wellfunded 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 lowend 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. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
Self-citationA Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342
Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.11 · Cited by 2,264 · cited 1×
“We retain the standard pretraining corpus of English Wikipedia and the Toronto BookCorpus (Zhu et al., 2015), containing 16GB of text, tokenized into subwords using BERT’s uncased tokenizer.”
MethodSpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00300 · Cited by 1,827
Self-citationSpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2019) · arXiv · doi:10.48550/arxiv.1907.10529 · Cited by 1,827
Self-citation
Cited by
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
Min, B., Ross, H., Sulem, E., Veyseh, A. P. B., Nguyen, T. H., Sainz, O., Agirre, E., Heintz, I., & Roth, D. (2024) · ACM Computing Surveys · doi:10.1145/3605943 · Cited by 1,387
“In line with this approach, Izsak et al. [72] propose software optimization and design choices for pre-training BERT in 24 hours using a single low-end deep learning server.”
MethodBiases in Large Language Models: Origins, Inventory, and Discussion
Navigli, R., Conia, S., & Ross, B. (2023) · Journal of Data and Information Quality · doi:10.1145/3597307 · Cited by 364
“Unfortunately, re-training language models is an expensive endeavor in terms of computational resources, especially in the case of academic budget [70], and annotating balanced corpora not only requires time and money but also inding expert annotators, which is especially di cult for low-resource languages.”
BackgroundTowards trustworthy LLMs: a review on debiasing and dehallucinating in large language models
Lin, Z., Guan, S., Zhang, W., Zhang, H., Li, Y., & Zhang, H. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10896-y · Cited by 141
Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Warstadt, A., Mueller, A., Choshen, L., Wilcox, E., Zhuang, C., Ciro, J., Mosquera, R., Paranjabe, B., Williams, A., Linzen, T., et al. (2023) · Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning · doi:10.18653/v1/2023.conll-babylm.1 · Cited by 74
Curriculum learning for language modeling
Campos, D. (2021) · arXiv · doi:10.48550/arxiv.2108.02170 · Cited by 15
“Moreover we do not find any evidence that any type of heuristic for difficulty to be more apt for CBC. Leveraging recent work on training BERT in an academic setting [18] we will explore how our top performing methods like trigram and random perform when their code becomes public.”
Metadata
- Authors
- Izsak, P., Berchansky, M., & Levy, O.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 10644-10652
- OpenAlex
- W3155183406
- Cited by
- 76
- References
- 14
- FWCI
- 5.55
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: How to Train BERT with an Academic Budget. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.831
- The paper
- Izsak, P., Berchansky, M., & Levy, O. (2021). How to Train BERT with an Academic Budget. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.831
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.