Papers › Reproducible scaling laws for contrastive language-image learning

Reproducible scaling laws for contrastive language-image learning

14 Dec 2022CVPR 2023 1arXiv:2212.07143archive 2025-07-28

Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, Jenia Jitsev

Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2212.07143")

Code

Syntology Ran 3 of 3 code samples harvested from 0 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong.

By repository: 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

laion-ai/scaling-laws-openclip officialmentioned in papermentioned on GitHubpytorch report
eify/open_clip mentioned on GitHubpytorchNOASSERTION report
mlfoundations/open_clip mentioned on GitHubpytorch report
nahidalam/open_clip mentioned on GitHubpytorchNOASSERTION 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.

Code Syntology ran Syntology

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
2ran · our draft was wrong

Licence: 3 of the 3 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.

Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

convert_to_custom_text_state_dict identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · f19962ebb134b3d7 · report
get_cast_dtype identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · dcd422d66b0581d8 · report
get_input_dtype identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · b476c8cfbf0f1f47 · report

Tasks

Image ClassificationOpen Vocabulary Attribute DetectionRetrievalZero-Shot Cross-Modal RetrievalZero-Shot Image ClassificationZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet OpenCLIP ViT-H/14 Top 1 Accuracy 88.5% #42 of 1060 Archive leaderboard report
Open Vocabulary Attribute Detection OVAD-Box benchmark Open CLIP ViT-B32 mean average precision 17.0 #6 of 7 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Image-to-text R@1 - #21 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Image-to-text R@10 - #21 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Image-to-text R@5 99.3 #21 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Text-to-image R@1 - #21 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Text-to-image R@10 - #21 of 22 Archive leaderboard report
Zero-Shot Cross-Modal Retrieval Flickr30k OpenCLIP VIT-H/14 Text-to-image R@5 94.1 #21 of 22 Archive leaderboard report
Zero-Shot Image Classification Country211 OpenClip H/14 (34B)(Laion2B) Top-1 accuracy 30.01 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIP

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