python (65.2k questions)
javascript (44.3k questions)
reactjs (22.7k questions)
java (20.8k questions)
c# (17.4k questions)
html (16.3k questions)
r (13.7k questions)
android (13k questions)
loading saved model doesn't behave as expected when finetuning it
I trained a pytorch model the accuracy at end of the first epoch is 20% and the loss value is 3.8 . I trained it until the loss is 3.2 and accuracy is around 50% and save it like this:
torch.save(mod...

Marzi Heidari
Votes: 0
Answers: 1
wandb getting logged without initiating
I do not want to use wandb. I don't even have an account. I am simply following this notebook for finetuning. I am not running the 2nd and 3 cells because I do not want to push the model to the hub.
H...
Kiera.K
Votes: 0
Answers: 1
fine-tuning bert for abstractive text summarization
I am using BERT (araBert to be more specific) for Arabic abstractive text summarization, but I don't want to train all the parameters from scratch. What I am looking for is a way to freeze the layers ...

Abd Al-Rahman Odeh
Votes: 0
Answers: 0
fine tuning with hugging face trainer when adding layer on eletra model
i'm trying to fine tune my own model with hugging face trainer module. There was no problem until just training ElectraforQuestionAnswering, however I tried to add additional layer on the model and tr...
장준서
Votes: 0
Answers: 0