Papers › On Layer Normalization in the Transformer Architecture

On Layer Normalization in the Transformer Architecture

12 Feb 2020ICML 2020 1arXiv:2002.04745archive 2025-07-28

Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Li-Wei Wang, Tie-Yan Liu

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 11 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

airi-institute/gena_lm mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoFormer: Enhanced Transformer with Rotary Position Embedding (arXiv:2104.09864; that paper's own run record: 14 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
blues-lin/fin-analyze mentioned on GitHubtfSyntology: not harvested report
colorfulscoop/tfdlg mentioned on GitHubtfMITSyntology: 11 samples, 10 ran (0 instrument-failed) · 1 unverified report
davidsvy/cosformer-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
facebookresearch/xformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Longformer: The Long-Document Transformer (arXiv:2004.05150; that paper's own run record: 22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified) and Self-attention Does Not Need O(n²) Memory (arXiv:2112.05682; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 6 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
noriyukipy/tfchat mentioned on GitHubtfMITSyntology: not harvested report
noriyukipy/tfdlg mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and The Curious Case of Neural Text Degeneration (arXiv:1904.09751; that paper's own run record: 10 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
yotaro-shimose/AttentionSolvesYourTSP mentioned on GitHubtfSyntology: not harvested report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
8ran
1unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from colorfulscoop/tfdlg. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

colorfulscoop/tfdlg community (archive-listed) 11 samples, 10 ran (0 instrument-failed) · 1 unverified
create_look_ahead_mask in 7 papers tfdlg/models.py ran MIT (permissive) · 868953286060f3a8 · report fixture: signature seq_len:int/0/int · returned EagerTensor · level recorded 2026-09-24
create_padding_mask in 11 papers tfdlg/models.py ran MIT (permissive) · fd2b714b8c2af39e · report fixture: signature seq:EagerTensor/2/int · returned EagerTensor · level recorded 2026-09-24
encode_dialog tfdlg/dialog/tokenizers.py ran MIT (permissive) · 22942e09fd44078d · report fixture: signature encode_fn:callable/0/?, sep_token_id:int/0/int, context:list/1/str, response:str/0/str · returned list · level recorded 2026-09-24
filter_bad_ids tfdlg/generations.py ran MIT (permissive) · 434564b8c9520cf5 · report fixture: signature bad_ids:list/1/int, dist:ndarray/2/float · returned ndarray · level recorded 2026-09-24
filter_to_topk tfdlg/generations.py ran MIT (permissive) · ec70453aadfa3cc2 · report fixture: signature top_k:int/0/int, dist:ndarray/2/float · returned ndarray · level recorded 2026-09-24
filter_to_topp tfdlg/generations.py ran · honoured contract fingerprinted MIT (permissive) · f10aa6a3b19fd64e · report fixture: signature top_p:float/0/float, dist:ndarray/2/float · returned ndarray · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
tfdlg/activations.py ran · honoured contract fingerprinted MIT (permissive) · d7b9cc73b75d3829 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
get in 42 papers tfdlg/activations.py ran MIT (permissive) · c1a80ebe76a998e9 · report fixture: signature identifier:str/0/str · returned function · level recorded 2026-09-24
import_class in 29 papers tfdlg/utils.py ran MIT (permissive) · 255a1a9413a38abc · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-24
scaled_dot_product_attention in 43 papers tfdlg/models.py ran MIT (permissive) · 3864ff9606edf68a · report fixture: signature q:EagerTensor/3/float, k:EagerTensor/3/float, v:EagerTensor/3/float, mask:EagerTensor/3/float, attention_dropout:callable/0/? · returned EagerTensor · level recorded 2026-09-24
load_model in 479 papers tfdlg/utils.py unverified MIT (permissive) · 932caee3efef6087 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections