thanks for this amazing tutorial at first.
So im not 100% sure if i got everything corretly according to your tutorial.
I am not able to open the files in jupyter, btw: where do i get the files? Can i directly open them from github?
Idk how but it works on my google Colab, there i was abl to get the files.
In the first lession you say: if this takes more than 5 min, its obvious that something goes wrong -> mine took about 30 mins and i even stopped it.
May you help me?
THis course seems to be super nice but not really good structured.
Hey you need a jupyter network runner to run ipynb notebooks. Colab is one option. you can run the notebooks on colab, or you can download anaconda for your local machine and run it from there. You’ll have to look up a tutorial on how, but its pretty easy.
As for running time, it really depends on hardware. Don’t worry about it too much, if it’s working fine then let it run. You will eventually understand the capabilities of your hardware and learn to work around it.
Hey. So on Colab it took so long as i told you in the course the prof says: if its more than 5 min something goes wrong. Mine took more than 20 min and i had 10 to go before i stopped it.
yeah that happens.
For example in the nlp lesson, the time on jeremy’s notebook is 11 minutes to train language model, my GTX 1050ti takes 3 hours for smaller batchsize and seq_len. So it really matters on hardware.
you can think of colab as a compiler for jupyter notebooks. Not exactly, but somewhat. So yeah you can use colab to do the courses. Another option is kaggle notebooks. see what works best for you. All the best
