setfit

setfit copied to clipboard

I trained a SetFitModel with a custom Pytorch head which is more complex than the inbuild and gives far superior results and I followed the instructions for building it from...

Ulipenitz

OscarRunsCode

`Training Loss` and `Validation Loss` are not logged

1

Hi, I'm following the [quick start guide](https://huggingface.co/docs/setfit/quickstart). And I add the `logging_steps` and `eval_steps` as the TrainingArguments. However, the `Training Loss` and `Validation Loss` are not logged. Details ``` from...

gxcuit

Hello, I just learn about SetFit and now I want to use it for my ABSA usecase. I have 50.000 row of datasets which the maximum token per row is...

Erland366

setfit model on multiple GPUs?

1

Now that sentence transformers support multiple gpus, i was wondering if setfit supports it also? does Anyone has any idea about setting the number of GPUs in the setfittrainer

twright8

AttributeError: 'TrainingArguments' object has no attribute 'eval_strategy'

1

Edit: I just saw there are other issues related to this: #535, #528, #512 and a PR #538 When running training as in the example in the README, I get...

HeAndres

setfit model performance advice

4

Hello gents, I was hoping I can get a second opinion about a situation I am facing while using setfit for a multi class classification use case. The dataset is...

rolandtannous

Hi, I trained a model with SetFitTrainer and afterwards started a hyperparameter optimization with the same parameters for testing reasons. The expected behaviour would be both of them having the...

HexadimensionalerAlp

Fixes #542

HeAndres

setfit can not get good result for chinese language?

1

The number of data labels is 4. the eval loss increase and the train loss decrease. I think it is overfit. Code is as below: # code ```from datasets import...

guangdongliang