Our Story
We wanted to use a different NLP model we hadn't before and Bert seemed like a great choice as it is overall one of the best NLP models that we were slightly familiar with. However, our model turned out to have a training time of about 300 hours. Which we tried to troubleshoot however didn't succeed in. Then we changed the model to DistilBERT which was working much better. Our training time was around 4 hours. It was about to finish training the first epoch but then it crashed. We tried to fix this however it only got worse. In the end, we tried our best even though we didn't succeed on this one model. We were still able to learn a lot. Queue Coldplay:
[Verse 1: Chris Martin] When you try your best, but you don't succeed When you get what you want, but not what you need When you feel so tired, but you can't sleep Stuck in reverse When the tears come streaming down your face When you lose something you can't replace When you love someone, but it goes to waste Could it be worse?
[Chorus: Chris & Will, Chris] Lights will guide you home And ignite your bones And I will try to fix you
[Verse 2: Chris Martin] And high up above or down below When you're too in love to let it go But if you never try, you'll never know Just what you're worth
[Chorus: Chris & Will, Chris] Lights will guide you home And ignite your bones And I will try to fix you Thank you for the opportunity!!!!
Built With
- python
- tensorflow
Log in or sign up for Devpost to join the conversation.