Papers › A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate,...

A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

26 Mar 2018arXiv:1803.09820archive 2025-07-28

Leslie N. Smith

Although deep learning has produced dazzling successes for applications of image, speech, and video processing in the past few years, most trainings are with suboptimal hyper-parameters, requiring unnecessarily long training times. Setting the hyper-parameters remains a black art that requires years of experience to acquire. This report proposes several efficient ways to set the hyper-parameters that significantly reduce training time and improves performance. Specifically, this report shows how to examine the training validation/test loss function for subtle clues of underfitting and overfitting and suggests guidelines for moving toward the optimal balance point. Then it discusses how to increase/decrease the learning rate/momentum to speed up training. Our experiments show that it is crucial to balance every manner of regularization for each dataset and architecture. Weight decay is used as a sample regularizer to show how its optimal value is tightly coupled with the learning rates and momentums. Files to help replicate the results reported here are available.

PaperPDFCodeCode 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

The archive's official repository (lnsmith54/hyperParam1) was not harvested; the 7 samples below come from 4 community repositories.

Syntology 7 code samples harvested from 4 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 4 repositories, 4 ran (3 with no instrument failure; 1 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

30 repositories listed; official and paper-mentioned ones first.

lnsmith54/hyperParam1 officialmentioned in paperSyntology: not harvested report
AbhimanyuAryan/ImageClassification mentioned on GitHubSyntology: not harvested report
AlexMGitHub/Checkers-MCTS mentioned on GitHubtfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
AmolMavuduru/CLRDeepLearning mentioned on GitHubSyntology: not harvested report
DrHB/fastai_wd mentioned on GitHubSyntology: not harvested report
GPUPhobia/vocal-mask mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decoupled Weight Decay Regularization (arXiv:1711.05101; that paper's own run record: 18 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified) and End-to-end music source separation: is it possible in the waveform domain? (arXiv:1810.12187; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
GilesStrong/Smith_HyperParams1_Demo mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
MatthewAlmeida/ActivityRecognitionKeras mentioned on GitHubtfSyntology: not harvested report
Niteeshaballa/fastai-practice mentioned on GitHubSyntology: not harvested report
Vakihito/SentimentYoutube mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ktrain: A Low-Code Library for Augmented Machine Learning (arXiv:2004.10703; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
asvcode/1_cycle mentioned on GitHubSyntology: not harvested report
bentrevett/pytorch-image-classification mentioned on GitHubpytorchMITSyntology: not harvested report
csvance/onecycle-cosine mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
datalass1/fastai mentioned on GitHubtfSyntology: not harvested report
ferhatkkochan/deeplearning-notes mentioned on GitHubSyntology: not harvested report
fkochan/deeplearning-notes mentioned on GitHubSyntology: not harvested report
gurucharanmk/PyTorch_OneCyclePolicyScheduler mentioned on GitHubpytorchMITSyntology: not harvested report
haritha91/1cycle-Policy-Experiment mentioned on GitHubpytorchSyntology: not harvested report
ifrit98/lr_range_test mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
jianshen92/stanford-car-grab-challenge mentioned on GitHubpytorchSyntology: not harvested report
nachiket273/One_Cycle_Policy mentioned on GitHubpytorchSyntology: not harvested report
nathanhubens/KerasOneCycle mentioned on GitHubSyntology: not harvested report
pukkapies/urop2019 mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-end learning for music audio tagging at scale (arXiv:1711.02520; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
rajs96/ULMFiT-Twitter-US-Airline-Sentiment mentioned on GitHubSyntology: not harvested report
rupaai/60DaysOfUdacity mentioned on GitHubpytorchSyntology: not harvested report
simongrest/farm-pin-crop-detection-challenge mentioned on GitHubApache-2.0Syntology: not harvested report
suhas1999/Flip-kart-grid-challenge mentioned on GitHubpytorchMITSyntology: not harvested report
ymittal23/PlayWithCifar mentioned on GitHubtfSyntology: not harvested report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-9 mindsporeSyntology: not harvested 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

7 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
1ran
3unverified

Licence: 2 of the 7 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

AlexMGitHub/Checkers-MCTS community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
save_nn_to_disk training_pipeline.py ran MIT (permissive) · ef6d4cd8f9f23f77 · report fixture: signature neural_network:callable/0/?, iteration:int/0/int, timestamp:str/0/str · returned str · level recorded 2026-09-26
plot_history training_pipeline.py unverified MIT (permissive) · ba3cf0e825859191 · report
states_to_piece_positions play_Checkers.py unverified MIT (permissive) · 13b8695d58380dd5 · report
GilesStrong/Smith_HyperParams1_Demo community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
AMS Modules/AMS.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 3dbd243a8c21052a · report fixture: signature s:float/0/float, b:float/0/float · returned float · level recorded 2026-09-22
amsScanQuick Modules/AMS.py ran · our draft was wrong Apache-2.0 (permissive) · a5ca0276a41b2558 · report fixture: signature inData:DataFrame/0/?, wFactor:float/0/float · returned tuple · level recorded 2026-09-22
csvance/onecycle-cosine community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
annealing_cos in 7 papers onecyclec.py ran · violated contract fingerprinted no licence file found · pointer only · c12d423641e370fe · report fixture: signature start:float/0/float, end:float/0/float, pct:float/0/float · returned float64 · level recorded 2026-09-22
ifrit98/lr_range_test community (archive-listed) 1 sample, 0 ran · 1 unverified
ploty lr_range_test/plot.py unverified no licence file found · pointer only · 01862d3a9e702e3b · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: 1cycle

1cycleSPEEDWeight Decay

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