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)

Questions - roberta

Hugging Face not able to reload all weights after training

I recently being using a RobertaLarge model, which I perform a down stream Training, using "Trainer" package. All goes well, I see the loss going down, and compare manually some results with...
test-img

Joao de Oliveira

python

huggingface-transformers

roberta

Votes: 0

Answers: 1

Latest Answer

I found out what was wrong. Will share with others, given others may have the same issue. My problem was that I wrapped my model into a DataParallel model = nn.DataParallel(model) So it seems that Tra...
test-img

Joao de Oliveira

How can i save model while training in torch

I am training RoBERTa model for a new language, and it takes some hours to train the data. So I think it is a good idea to save the model while training so that I can continue training the model from ...
test-img

robel

python

deep-learning

torch

huggingface-transformers

roberta

Votes: 0

Answers: 1

Latest Answer

You can use the Trainer from transformers to train the model. This trainer will also need you to specify the TrainingArguments, which will allow you to save checkpoints of the model while training. So...
test-img

Eric Lozano

NER Classification Deberta Tokenizer error : You need to instantiate DebertaTokenizerFast

I'm trying to perform a NER Classification task using Deberta, but I'm stacked with a Tokenizer error. This is my code (my input sentence must be splitted word by word by ",:): from transformers ...
test-img

Chiara

python

tokenize

bert-language-model

named-entity-recognition

roberta

Votes: 0

Answers: 1

Latest Answer

Lets try this: input_ids = [1, 31414, 6, 42, 16, 65, 3645, 328, 2] input_ids = ','.join(map(str, input_ids )) input_ids = ["Hello", ",", "this", "is", "...
test-img

Mahsa Hassankashi

Error(s) in loading state_dict for RobertaForSequenceClassification

I am using a fine-tuned Roberta Model that is unbiased-toxic-roberta trained on Jigsaw Data: https://huggingface.co/unitary/unbiased-toxic-roberta It is fine-tuned on 16 classes. I am writing my code ...
test-img

MAC

python-3.x

pytorch

huggingface-transformers

roberta

Votes: 0

Answers: 1

Latest Answer

Load with ignore_mismatched_sizes=True: model = tr.RobertaForSequenceClassification.from_pretrained( "/home/pc/unbiased_toxic_roberta", num_labels=2, ignore_mismatched_sizes=True...
test-img

joe32140

Posts

Questions

Blogs

Jobs