Papers › Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

23 Apr 2020ACL 2020 6arXiv:2004.10964archive 2025-07-28

Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the domain of a target task. We present a study across four domains (biomedical and computer science publications, news, and reviews) and eight classification tasks, showing that a second phase of pretraining in-domain (domain-adaptive pretraining) leads to performance gains, under both high- and low-resource settings. Moreover, adapting to the task's unlabeled data (task-adaptive pretraining) improves performance even after domain-adaptive pretraining. Finally, we show that adapting to a task corpus augmented using simple data selection strategies is an effective alternative, especially when resources for domain-adaptive pretraining might be unavailable. Overall, we consistently find that multi-phase adaptive pretraining offers large gains in task performance.

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

The archive's official repository (allenai/dont-stop-pretraining) was not harvested; the 13 samples below come from 2 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 14 code samples: 13 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 14: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 13 samples from 2 repositories, 12 ran (8 with no instrument failure; 4 where Syntology's instrument failed); 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 13 samples that ran have no recorded date.

allenai/dont-stop-pretraining officialmentioned in paperpytorchSyntology: not harvested report
SUSTechBruce/G-MAP mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
bionlu-coling2024/biomed-ner-intent_detection mentioned on GitHubpytorchSyntology: not harvested report
sagjounkani/Dont-Stop-Pretraining-Use-Adapters-Instead mentioned on GitHubpytorchSyntology: not harvested report
shizhediao/black-box-prompt-learning mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Black-box Prompt Learning for Pre-trained Language Models (arXiv:2201.08531; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
shizhediao/t-dna mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (3 instrument-failed) · 1 unverified 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 5 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
7ran
1unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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. 1 sample is listed last, in a group without a repository. “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.

SUSTechBruce/G-MAP community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
set_output_dir domain_qa_ner/mem_roberta/run_finetune_qa_medication.py ran · our draft was wrong MIT (permissive) · bbc63fe66d3ee4d0 · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-22
shizhediao/t-dna community (archive-listed) 12 samples, 11 ran (3 instrument-failed) · 1 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
TDNA/util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
default_compute_objective TDNA/trainer.py ran Apache-2.0 (permissive) · ada7a524687a5b73 · report fixture: signature metrics:dict/0/? · returned float · level recorded 2026-09-24
find_pruneable_heads_and_indices in 19 papers TDNA/modeling.py ran Apache-2.0 (permissive) · 1b4bc5e6ef0e9288 · report fixture: signature heads:list/1/int, n_heads:int/0/int, head_size:int/0/int, already_pruned_heads:set/0/? · returned tuple · level recorded 2026-09-24
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input
TDNA/util.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · aef07bb1e2787431 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_constant_schedule in 21 papers TDNA/optimization.py ran Apache-2.0 (permissive) · 0cfd32e6d6d4419a · report fixture: signature optimizer:SGD/0/?, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_constant_schedule_with_warmup in 25 papers TDNA/optimization.py ran Apache-2.0 (permissive) · 2eeaa920a743dccc · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_linear_schedule_with_warmup in 39 papers TDNA/optimization.py ran · our draft was wrong Apache-2.0 (permissive) · 5bf56e40b4301199 · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-22
get_pairs in 260 papers TDNA/tokenization.py ran Apache-2.0 (permissive) · b50994ad24f6d583 · report fixture: signature word:str/0/str · returned set · level recorded 2026-09-25
hf_bucket_url in 13 papers TDNA/modeling.py ran Apache-2.0 (permissive) · 3cbbdc1cef27d05d · report fixture: signature model_id:str/0/str, filename:str/0/str, use_cdn:bool/0/bool, mirror:NoneType/0/? · returned str · level recorded 2026-09-24
is_remote_url in 23 papers TDNA/modeling.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 899d1e2736236351 · report fixture: signature url_or_filename:str/0/str · returned bool · level recorded 2026-09-24
nested_concat TDNA/trainer.py ran Apache-2.0 (permissive) · 8c6f5dccbea60d03 · report fixture: signature tensors:tuple/1/Tensor, new_tensors:tuple/1/Tensor, dim:int/0/int · returned tuple · level recorded 2026-09-24
get_logger in 383 papers TDNA/util.py unverified Apache-2.0 (permissive) · 925a37d315d717fb · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
to_list in 62 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 9df40357afea56cc · report fixture: signature tensor:Tensor/2/float · returned list · level recorded, date not recorded

Tasks

Citation Intent Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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