# \#nightly **URL:** https://support.prodi.gy/tag/nightly/65.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Script: Load data in spaCy v3's .spacy format](https://support.prodi.gy/t/script-load-data-in-spacy-v3s-spacy-format/4369)
**Author:** [@ines](https://support.prodi.gy/u/ines)\ **Replies:** 4\ **Last updated:** [January 21, 2023, 10:32am UTC](https://support.prodi.gy/t/script-load-data-in-spacy-v3s-spacy-format/4369 "2023-01-21T10:32:26Z")
This topic came up in the Prodigy nightly thread: it'd be cool to have Prodigy load data and annotations in spaCy v3's new binary .spacy format, which is a serialized collection of Doc objects (DocBin) under the hood. Ho… --- ## [Changing the UI doesn't add more text on screen](https://support.prodi.gy/t/changing-the-ui-doesnt-add-more-text-on-screen/4150)
**Author:** [@tristan19954](https://support.prodi.gy/u/tristan19954)\ **Replies:** 2\ **Last updated:** [May 3, 2022, 2:53pm UTC](https://support.prodi.gy/t/changing-the-ui-doesnt-add-more-text-on-screen/4150 "2022-05-03T14:53:36Z")
Hello, I have been busy annotating data and I am trying to change the UI of prodigy to allow more text at once on the screen. The main reason that I want to do that is that I am doing a ner.correct and there are fairly… --- ## [Convert spacy binary data to jsonl](https://support.prodi.gy/t/convert-spacy-binary-data-to-jsonl/4113)
**Author:** [@tristan19954](https://support.prodi.gy/u/tristan19954)\ **Replies:** 5\ **Last updated:** [April 28, 2022, 6:07am UTC](https://support.prodi.gy/t/convert-spacy-binary-data-to-jsonl/4113 "2022-04-28T06:07:55Z")
Hello, I just recently got prodigy, and before that I was using another free program to annotate data for my spacy model. From this program, I could download my annotated data in iob format which I then converted to spa… --- ## [✨ Prodigy nightly: spaCy v3 support, UI for overlapping spans & more](https://support.prodi.gy/t/prodigy-nightly-spacy-v3-support-ui-for-overlapping-spans-more/3861)
**Author:** [@ines](https://support.prodi.gy/u/ines)\ **Replies:** 110\ **Last updated:** [January 20, 2022, 4:13pm UTC](https://support.prodi.gy/t/prodigy-nightly-spacy-v3-support-ui-for-overlapping-spans-more/3861 "2022-01-20T16:13:02Z")
Edit (2021-08-12): Prodigy v1.11 is out now :raising\_hands: See the release notes here: Changelog · Prodigy · An annotation tool for AI, Machine Learning & NLP As mentioned in this thread, now that spaCy v3.0 is out we … --- ## [ner.teach - couple of questions](https://support.prodi.gy/t/ner-teach-couple-of-questions/4385)
**Author:** [@lnatprodigy](https://support.prodi.gy/u/lnatprodigy)\ **Replies:** 9\ **Last updated:** [December 30, 2021, 2:02pm UTC](https://support.prodi.gy/t/ner-teach-couple-of-questions/4385 "2021-12-30T14:02:54Z")
Hi, I've trained a model with gold-std data and now I want to improve it by using ner.teach. The problem is that prodigy seems to show score 1.0 for almost all it's suggestions and the vast majority of it's suggestions… --- ## [ner.teach transformer model server error](https://support.prodi.gy/t/ner-teach-transformer-model-server-error/4307)
**Author:** [@mcmchattr](https://support.prodi.gy/u/mcmchattr)\ **Replies:** 1\ **Last updated:** [September 2, 2021, 12:07pm UTC](https://support.prodi.gy/t/ner-teach-transformer-model-server-error/4307 "2021-09-02T12:07:03Z")
Hello, I am trying to refine a transformer based ner model using ner.teach on the 1.11(0a8) release. Per this thread, I will check out the regular release for ner.teach. However, I also wanted to report that I am regul… --- ## [Duplicates in ner.correct using 1.11.0a8](https://support.prodi.gy/t/duplicates-in-ner-correct-using-1-11-0a8/4516)
**Author:** [@daqieq](https://support.prodi.gy/u/daqieq)\ **Replies:** 3\ **Last updated:** [August 4, 2021, 10:03pm UTC](https://support.prodi.gy/t/duplicates-in-ner-correct-using-1-11-0a8/4516 "2021-08-04T22:03:18Z")
Similar issue to Duplicates in ner.correct in 1.10.2, except I'm using SpaCy 3.0.6 and Prodigy 1.11.0a8. I'm getting roughly 20 examples to correct with each invocation of the ner.correct session. Originally I tagged NE… --- ## [Optional ner.correct argument --update error](https://support.prodi.gy/t/optional-ner-correct-argument-update-error/4046)
**Author:** [@lejimmy](https://support.prodi.gy/u/lejimmy)\ **Replies:** 4\ **Last updated:** [April 25, 2021, 5:21am UTC](https://support.prodi.gy/t/optional-ner-correct-argument-update-error/4046 "2021-04-25T05:21:07Z")
Saving annotations when the --update option using ner.teach results in the following error: if span\["answer"\] == "accept" KeyError: 'answer'. Without the --update option, saving annotations works fine. --- ## [Possible bug in nightly ner.correct](https://support.prodi.gy/t/possible-bug-in-nightly-ner-correct/4453)
**Author:** [@dsr2021](https://support.prodi.gy/u/dsr2021)\ **Replies:** 1\ **Last updated:** [July 19, 2021, 12:56am UTC](https://support.prodi.gy/t/possible-bug-in-nightly-ner-correct/4453 "2021-07-19T00:56:29Z")
I got an error with a stacktrace when trying to save annotations for a new dataset. The last few lines are File "C:\\NLP\\venv\\lib\\site-packages\\prodigy\\recipes\\ner.py", line 266, in doc.char\_span(span\["start"\], span\["e… --- ## [Train binary textcat in Prodigy Nightly](https://support.prodi.gy/t/train-binary-textcat-in-prodigy-nightly/4451)
**Author:** [@lifan](https://support.prodi.gy/u/lifan)\ **Replies:** 3\ **Last updated:** [July 19, 2021, 8:22am UTC](https://support.prodi.gy/t/train-binary-textcat-in-prodigy-nightly/4451 "2021-07-19T08:22:30Z")
Hello community, I am new to Prodigy and currently I am using the nightly version. I can't figure out how to train a textcat model with binary label (https://prodi.gy/docs/text-classification#manual-binary). The score i… --- ## [Better score with learning-curve than with train?](https://support.prodi.gy/t/better-score-with-learning-curve-than-with-train/4447)
**Author:** [@lnatprodigy](https://support.prodi.gy/u/lnatprodigy)\ **Replies:** 4\ **Last updated:** [July 18, 2021, 7:02am UTC](https://support.prodi.gy/t/better-score-with-learning-curve-than-with-train/4447 "2021-07-18T07:02:20Z")
Hi, I use prodigy to annotate data but I generally use spacy to train the model. What confuses me is that when I run training-curve on my dataset, the model actually reaches a higher score, than when I train the model (… --- ## [Misaligned entities only in train-curve](https://support.prodi.gy/t/misaligned-entities-only-in-train-curve/4412)
**Author:** [@lnatprodigy](https://support.prodi.gy/u/lnatprodigy)\ **Replies:** 4\ **Last updated:** [July 8, 2021, 4:54am UTC](https://support.prodi.gy/t/misaligned-entities-only-in-train-curve/4412 "2021-07-08T04:54:21Z")
Hey @ines I hope it's okay if I ask a follow-up in here. I went ahead and added the encoding="utf-8" directly in my site-packages and the recipe runs now. I get the following warning though: entities=ent\_str\[:50\] + "… --- ## [Encoding Error when running train-curve](https://support.prodi.gy/t/encoding-error-when-running-train-curve/4406)
**Author:** [@lnatprodigy](https://support.prodi.gy/u/lnatprodigy)\ **Replies:** 9\ **Last updated:** [July 5, 2021, 7:09am UTC](https://support.prodi.gy/t/encoding-error-when-running-train-curve/4406 "2021-07-05T07:09:08Z")
Hi, I was wanting to try the train-curve recipe but I get the followin error when I run it: Traceback (most recent call last): File "C:\\Users\\x\\AppData\\Local\\Programs\\Python\\Python37\\Lib\\runpy.py", line 193, in \_run\_… --- ## [Loading a text file](https://support.prodi.gy/t/loading-a-text-file/4404)
**Author:** [@dsr2021](https://support.prodi.gy/u/dsr2021)\ **Replies:** 4\ **Last updated:** [July 5, 2021, 12:51am UTC](https://support.prodi.gy/t/loading-a-text-file/4404 "2021-07-05T00:51:58Z")
I'm new to using prodigy. I'm trying to annotate a simple text file using the en\_core\_web\_lg model. However, in the web UI, I see only the title of the article. The format of the file is, title, blank line, paragraphs s… --- ## [Error when using data-to-spacy](https://support.prodi.gy/t/error-when-using-data-to-spacy/4370)
**Author:** [@lnatprodigy](https://support.prodi.gy/u/lnatprodigy)\ **Replies:** 3\ **Last updated:** [June 28, 2021, 1:12pm UTC](https://support.prodi.gy/t/error-when-using-data-to-spacy/4370 "2021-06-28T13:12:05Z")
Hi, I'm using a custom tokenizer so far I've had no issues training a model with that custom tokenizer and using that model in prodigy to help me annotate data for a NER task. However when I want to export the data wit… --- ## [Use custom tokenizer in data-to-spacy](https://support.prodi.gy/t/use-custom-tokenizer-in-data-to-spacy/4324)
**Author:** [@nsantacruz](https://support.prodi.gy/u/nsantacruz)\ **Replies:** 9\ **Last updated:** [June 17, 2021, 1:32pm UTC](https://support.prodi.gy/t/use-custom-tokenizer-in-data-to-spacy/4324 "2021-06-17T13:32:59Z")
I have a follow-up question to this topic. I used data-to-spacy with the following parameters prodigy data-to-spacy output --ner my\_dataset --ner-missing --base-model output/my\_model/model-last -F functions.py I'm incl… --- ## [Flag --batch-size not recognized by prodigy train](https://support.prodi.gy/t/flag-batch-size-not-recognized-by-prodigy-train/4236)
**Author:** [@rindranirina](https://support.prodi.gy/u/rindranirina)\ **Replies:** 3\ **Last updated:** [May 20, 2021, 11:27am UTC](https://support.prodi.gy/t/flag-batch-size-not-recognized-by-prodigy-train/4236 "2021-05-20T11:27:43Z")
I am using the nightly version 1.11.0a8 and when I run prodigy train with --batch-size flag, an exception is raised for "no such option". The current documentation has many flags for training e.g. --n-iter, --dropout and… --- ## [How to extract dev set from prodigy train recipe](https://support.prodi.gy/t/how-to-extract-dev-set-from-prodigy-train-recipe/4237)
**Author:** [@rindranirina](https://support.prodi.gy/u/rindranirina)\ **Replies:** 2\ **Last updated:** [May 20, 2021, 1:20am UTC](https://support.prodi.gy/t/how-to-extract-dev-set-from-prodigy-train-recipe/4237 "2021-05-20T01:20:52Z")
I am using the nightly version 1.11.0a8. I use prodigy train recipe for training an NER model using a small dataset. So I have used -es flag to split train and evaluation sets. Now, I want to visualize and ab-test the … --- ## [ner.eval-ab: should \`mapping\` columns match the choice in \`accept\` column?](https://support.prodi.gy/t/ner-eval-ab-should-mapping-columns-match-the-choice-in-accept-column/4185)
**Author:** [@aviss](https://support.prodi.gy/u/aviss)\ **Replies:** 2\ **Last updated:** [May 4, 2021, 12:59pm UTC](https://support.prodi.gy/t/ner-eval-ab-should-mapping-columns-match-the-choice-in-accept-column/4185 "2021-05-04T12:59:12Z")
I ran the ner.eval-ab recipe and wanted to explore the rejected examples from my model B (I assume this is the model you pass second). I'm confused by different values in the column accept (which should give me the mode… --- ## [ner.teach works well for first few tags, then starts suggesting random / weird annotations](https://support.prodi.gy/t/ner-teach-works-well-for-first-few-tags-then-starts-suggesting-random-weird-annotations/4176)
**Author:** [@tristan19954](https://support.prodi.gy/u/tristan19954)\ **Replies:** 2\ **Last updated:** [April 28, 2021, 1:19pm UTC](https://support.prodi.gy/t/ner-teach-works-well-for-first-few-tags-then-starts-suggesting-random-weird-annotations/4176 "2021-04-28T13:19:45Z")
Hello, I have a transformer model with a F-score of 0.78 that I would like to attempt to increase while using ner.teach. I have thus been busy gathering a large amount of raw text and now that I did that I started tryi… --- ## [terms.teach not working for nightly](https://support.prodi.gy/t/terms-teach-not-working-for-nightly/4165)
**Author:** [@Debojit](https://support.prodi.gy/u/Debojit)\ **Replies:** 3\ **Last updated:** [April 25, 2021, 5:27am UTC](https://support.prodi.gy/t/terms-teach-not-working-for-nightly/4165 "2021-04-25T05:27:53Z")
Hi, I have spacy 3.0.5 and nightly 1.11.0a. I was following " Training a NAMED ENTITY RECOGNITION MODEL with Prodigy and Transfer Learning" and used command for 1st level of teaching it is working prodigy sense2vec.tea… --- ## [ArgumentError for prodigy train on v1.11.0a6](https://support.prodi.gy/t/argumenterror-for-prodigy-train-on-v1-11-0a6/4132)
**Author:** [@jamiehannaford](https://support.prodi.gy/u/jamiehannaford)\ **Replies:** 2\ **Last updated:** [April 14, 2021, 1:21am UTC](https://support.prodi.gy/t/argumenterror-for-prodigy-train-on-v1-11-0a6/4132 "2021-04-14T01:21:44Z")
:wave: When using prodigy train (and a few other commands), I receive this error on v1.11.0a6: Traceback (most recent call last): File "/Users/jamie/.pyenv/versions/3.8.7/lib/python3.8/runpy.py", line 194, in \_run\_mod… --- ## [prodigy nightly - can only do 10 annotations at a time?](https://support.prodi.gy/t/prodigy-nightly-can-only-do-10-annotations-at-a-time/3934)
**Author:** [@mumud123](https://support.prodi.gy/u/mumud123)\ **Replies:** 13\ **Last updated:** [April 13, 2021, 6:34pm UTC](https://support.prodi.gy/t/prodigy-nightly-can-only-do-10-annotations-at-a-time/3934 "2021-04-13T18:34:44Z")
Hi I'm just trying out the prodigy nightly -- I have a dataset with over 1000 data samples. However, when I run prodigy, it runs out of data after 10 samples. If I refresh my browser, I get another 10, and it runs out ag… --- ## [Could not find function 'specialized\_ner\_reader' in function registry 'readers'.](https://support.prodi.gy/t/could-not-find-function-specialized-ner-reader-in-function-registry-readers/4109)
**Author:** [@fra-csl](https://support.prodi.gy/u/fra-csl)\ **Replies:** 7\ **Last updated:** [April 12, 2021, 7:12am UTC](https://support.prodi.gy/t/could-not-find-function-specialized-ner-reader-in-function-registry-readers/4109 "2021-04-12T07:12:00Z")
Dear Prodigy Support, I recently got the Prodigy Nightly plan and I wanted to try to use the new features of data-to-spacy (see e.g. here) in order to generate a config.cfg file to use with the new spacy 3.0. Context I… --- ## [Output model in Prodigy Nightly](https://support.prodi.gy/t/output-model-in-prodigy-nightly/4030)
**Author:** [@a.arranz](https://support.prodi.gy/u/a.arranz)\ **Replies:** 5\ **Last updated:** [March 20, 2021, 12:28am UTC](https://support.prodi.gy/t/output-model-in-prodigy-nightly/4030 "2021-03-20T00:28:09Z")
Hi, I have been having some problems outputting my trained data to a temporary database. When I run the following command: prodigy train --ner dow30\_data output\_dir --./tmp\_dow30\_model I receive this in return: … --- ## [Prodigy nightly: "Invalid config override 'posts\_df\_random\_train': name should start with --"](https://support.prodi.gy/t/prodigy-nightly-invalid-config-override-posts-df-random-train-name-should-start-with/3965)
**Author:** [@oliver.mueller](https://support.prodi.gy/u/oliver.mueller)\ **Replies:** 2\ **Last updated:** [March 2, 2021, 8:39pm UTC](https://support.prodi.gy/t/prodigy-nightly-invalid-config-override-posts-df-random-train-name-should-start-with/3965 "2021-03-02T20:39:11Z")
Hi, I have installed the latest version of Prodigy nightly (and Spacy V3) and try to execute this recipe command: prodigy train ner posts\_df\_random\_train en\_core\_web\_md --eval-id posts\_df\_random\_test --output ./crowdsc… --- ## [(nightly) OSError: \[E053\] Could not read config.cfg](https://support.prodi.gy/t/nightly-oserror-e053-could-not-read-config-cfg/3928)
**Author:** [@xD3CODER](https://support.prodi.gy/u/xD3CODER)\ **Replies:** 7\ **Last updated:** [February 24, 2021, 2:24pm UTC](https://support.prodi.gy/t/nightly-oserror-e053-could-not-read-config-cfg/3928 "2021-02-24T14:24:54Z")
Hi, I just joined the nightly program of Prodigy, first thank's for this amazing tool ! I have encountered this issue when I try to run train on an ner dataset. The dataset has been exported from the stable version of… --- ## [Model en\_pipeline is incompatible with current version](https://support.prodi.gy/t/model-en-pipeline-is-incompatible-with-current-version/3932)
**Author:** [@Onyoursix](https://support.prodi.gy/u/Onyoursix)\ **Replies:** 2\ **Last updated:** [February 24, 2021, 12:17am UTC](https://support.prodi.gy/t/model-en-pipeline-is-incompatible-with-current-version/3932 "2021-02-24T00:17:44Z")
While doing some annotations using rel.manual I started to see this message come up after annotating about 10 documents. UserWarning: \[W095\] Model 'en\_pipeline' (0.0.0) requires spaCy \>=3.0.3,\<3.1.0 and is incompatible …