search

Neph0s / LMKE

Code for the paper 'Language Models as Knowledge Embeddings'
53 stars 7 forks source link

How long it took to run a model? #1

Closed zhiweihu1103 closed 1 year ago

zhiweihu1103 commented 2 years ago

I ran the program on the V100 using the script below, but it takes 42 minutes to run one epoch, I want to ask how long it took you to run the model? python main.py --batch_size 16 --plm bert --contrastive --self_adversarial --data wn18rr --task LP

Neph0s commented 2 years ago

Thanks for your interest. Generally, it takes around 80 epochs to achieve its best performance on the dev set under the default setting.

zhiweihu1103 commented 2 years ago

Then the epoch of training around 40 minutes is normal, right?

Neph0s commented 2 years ago

Yes, since language models are time-consuming compared with traditional KEs like TransE. You can also try using bert-tiny as the base model, which runs much faster, and achieves comparable performance on FB15K-237.

zhiweihu1103 commented 2 years ago

OK, I will try. Thank you for your reply. Good luck.