setfit

setfit copied to clipboard

No predictions from setfit

5

I ran SetFitTrainer to train the model with 5 classes (used multi_target_strategy="one-vs-rest"). My target variable was one hot encoded. When I get my predictions on the test data, I observe...

simran-padam

How to weight loss function

9

I have an extreme imbalanced dataset for muticlass task . To handle the imbalance, I want to weight loss function

freecui

Dealing with imbalanced classes

1

Hi, I have 9 classes which are imbalanced. The smallest one has 42 examples and the tallest one 95. I cannot downsample the bigger classes since I need all these...

Matthieu-Tinycoaching

How do I run multiple training runs on different GPU devices? I don't see any argument which allows me to set this. Thank you!

vahuja4

From which number of training samples does it not make sense anymore to use SetFit?

1

I'm building a classifier that assigns news articles to one of 8 categories, I was wondering if there was a rule of thumb that over a certain number of training...

lbelpaire

One-hot encoded label for multi class dont work with non-default loss_class (eg:BatchHardTripletLoss, ...) Note: Not using SetfitHead, but scikit learn one-vs-rest. `TypeError: unhashable type: 'list'` The error comes from line...

ps24601

Question: How the number of categories affect the training and accuracy?

8

I have found that increasing the number of categories reduce the accuracy results. Has anyone studied how the increased number of samples per category affect the results?

rubensmau

It's common that one might want to use setfit for classifying documents that are longer than max_token_len. There are several strategies for handling long documents, and the efficacy of each...

turian

I'd like to finetune setfit for ranking. Where, for each instance, there are possible text anwers in a ranked order. I'd then like to finetune to maintain the ranking. Would...

turian

Data without negative examples

2

Hi I was studying active learning integration using setfit with argilla Turns out I was using a small dataset, only 5 examples in each round, i.e. active learning trained the...

LordWaif