# Running on CPU **URL:** \ **Category:** Uncategorized\ **Tags:** usage, solved, training\ **Created:** [February 3, 2022, 11:07am UTC](https://support.prodi.gy/t/running-on-cpu/5274 "2022-02-03T11:07:03Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![EM22](https://avatars.discourse-cdn.com/v4/letter/e/db5fbb/32.png) [@EM22](https://support.prodi.gy/u/EM22)\ **Post date:** [February 3, 2022, 11:07am UTC](https://support.prodi.gy/t/running-on-cpu/5274/1 "2022-02-03T11:07:03Z")
Hi, Is it possible to train in Prodigy on cpu without gpu? I am currently getting the following warning with the train recipe, running on an Amazon ec2 instance (cpu only): UserWarning: User provided device\_type of 'cuda', but CUDA is not available. After which the process is immediately killed. ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [February 3, 2022, 12:40pm UTC](https://support.prodi.gy/t/running-on-cpu/5274/2 "2022-02-03T12:40:35Z")
Hi! Prodigy's `train` workflow is a little wrapper around spaCy's `train` command, which will train on CPU by default. If you're not providing a `--gpu-id` on the command line, it should train on CPU. Can you share the full command you're running and the full traceback that includes where the warning happened? ---
**Author:** ![EM22](https://avatars.discourse-cdn.com/v4/letter/e/db5fbb/32.png) [@EM22](https://support.prodi.gy/u/EM22)\ **Post date:** [February 3, 2022, 12:49pm UTC](https://support.prodi.gy/t/running-on-cpu/5274/3 "2022-02-03T12:49:27Z")
Thank you for your quick response! I am running the command: prodigy train my\_model --ner my\_dataset -m en\_core\_web\_trf and getting back: ========================= Generating Prodigy config ========================= ℹ Auto-generating config with spaCy ℹ Using config from base model ✔ Generated training config =========================== Initializing pipeline =========================== [2022-02-03 12:44:09,141] [INFO] Set up nlp object from config Components: ner Merging training and evaluation data for 1 components - [ner] Training: 392 | Evaluation: 97 (20% split) Training: 338 | Evaluation: 92 Labels: ner (5) [2022-02-03 12:44:09,243] [INFO] Pipeline: ['tok2vec', 'transformer', 'tagger', 'parser', 'attribute\_ruler', 'lemmatizer', 'ner'] [2022-02-03 12:44:09,243] [INFO] Resuming training for: ['ner', 'transformer'] [2022-02-03 12:44:09,251] [INFO] Created vocabulary [2022-02-03 12:44:09,252] [INFO] Finished initializing nlp object [2022-02-03 12:44:09,628] [INFO] Initialized pipeline components: ['tok2vec'] ✔ Initialized pipeline ============================= Training pipeline ============================= Components: ner Merging training and evaluation data for 1 components - [ner] Training: 392 | Evaluation: 97 (20% split) Training: 338 | Evaluation: 92 Labels: ner (5) ℹ Pipeline: ['tok2vec', 'transformer', 'tagger', 'parser', 'attribute\_ruler', 'lemmatizer', 'ner'] ℹ Frozen components: ['tagger', 'parser', 'attribute\_ruler', 'lemmatizer'] ℹ Initial learn rate: 0.0 E # LOSS TOK2VEC LOSS TRANS... LOSS NER ENTS\_F ENTS\_P ENTS\_R SPEED SCORE * * * Token indices sequence length is longer than the specified maximum sequence length for this model (776 \> 512). Running this sequence through the model will result in indexing errors /usr/local/lib64/python3.7/site-packages/torch/autocast\_mode.py:141: UserWarning: User provided device\_type of 'cuda', but CUDA is not available. Disabling warnings.warn('User provided device\_type of 'cuda', but CUDA is not available. Disabling') 0 0 0.00 143.00 226.19 17.08 20.00 14.91 59.10 0.17 Killed What do you think could be the problem? ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [February 3, 2022, 1:08pm UTC](https://support.prodi.gy/t/running-on-cpu/5274/4 "2022-02-03T13:08:13Z")
Thanks for the details! And I think the problem here might just be that you're running out of memory trying to train a transformer-based pipeline on CPU. For that, it typically makes more sense to train on a GPU. If you just want to run a quick training experiment to see if your data is good and your model is learning, you can just use one of the non-transformer pipelines instead, e.g. `en_core_web_lg` (with word vectors) or even `en_core_web_sm` (without word vectors). This should give you similar signals and insights – and if the results look promising, you can then export your data and train a transformer-based pipeline on a GPU, which should give you another boost in accuracy. (And if your model isn't learning or there are problems, you usually want to go and work on the data first.) ---
**Author:** ![EM22](https://avatars.discourse-cdn.com/v4/letter/e/db5fbb/32.png) [@EM22](https://support.prodi.gy/u/EM22)\ **Post date:** [February 3, 2022, 1:20pm UTC](https://support.prodi.gy/t/running-on-cpu/5274/5 "2022-02-03T13:20:11Z")
Thank you! We'll definitely try experimenting with one of the other models first and then take it from there. This was very helpful, thanks again!