{"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/transformers-without-tears-improving-the","title":"Transformers without Tears: Improving the Normalization of Self-Attention","arxiv_id":"1910.05895","date":"2019-10-14","proceeding":"EMNLP (IWSLT) 2019 11","authors":["Toan Q. Nguyen","Julian Salazar"],"abstract":"We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PreNorm) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, we propose $\\ell_2$ normalization with a single scale parameter (ScaleNorm) for faster training and better performance. Finally, we reaffirm the effectiveness of normalizing word embeddings to a fixed length (FixNorm). On five low-resource translation pairs from TED Talks-based corpora, these changes always converge, giving an average +1.1 BLEU over state-of-the-art bilingual baselines and a new 32.8 BLEU on IWSLT'15 English-Vietnamese. We observe sharper performance curves, more consistent gradient norms, and a linear relationship between activation scaling and decoder depth. Surprisingly, in the high-resource setting (WMT'14 English-German), ScaleNorm and FixNorm remain competitive but PreNorm degrades performance.","url_abs":"https://arxiv.org/abs/1910.05895v2","url_pdf":"https://arxiv.org/pdf/1910.05895v2.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":"transformers-without-tears-improving-the","repo_url":"https://github.com/tnq177/transformers_without_tears","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transformers-without-tears-improving-the","repo_url":"https://github.com/JunnYu/x-transformers-paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"transformers-without-tears-improving-the","repo_url":"https://github.com/facebookresearch/xformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transformers-without-tears-improving-the","repo_url":"https://github.com/MindCode-4/code-2/tree/main/persimmon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"transformers-without-tears-improving-the","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-1/persimmon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-english-1","task":"Machine Translation","dataset":"IWSLT2015 English-Vietnamese","model":"Transformer+BPE+FixNorm+ScaleNorm","rank_in_archive_order":4,"of":11,"metrics":{"BLEU":"32.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1910.05895","atlas_url":"https://app.syntology.ai/?focus=1910.05895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05895"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-1/persimmon","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tnq177/transformers_without_tears","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JunnYu/x-transformers-paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-2/tree/main/persimmon","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/xformers","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"c3d343d98dd98578","entry":"format_seconds","repo":"tnq177/transformers_without_tears","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tnq177/transformers_without_tears/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3d343d98dd98578"}},{"code_sha256_prefix":"6375f131987193cf","entry":"get_logger","repo":"tnq177/transformers_without_tears","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tnq177/transformers_without_tears/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6375f131987193cf"}},{"code_sha256_prefix":"faf7e5eb8af5a1a2","entry":"init_vocab","repo":"tnq177/transformers_without_tears","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tnq177/transformers_without_tears/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"faf7e5eb8af5a1a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}