# IndexError: tuple index out of range

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findexerror-tuple-index-out-of-range%2F10986%3E%5C
**Category:** Beginners\
**Created:** [October 21, 2021, 11:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findexerror-tuple-index-out-of-range%2F10986 "2021-10-21T23:11:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Nexsus](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nexsus/32/2932_2.png) [@Nexsus](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FNexsus)%5C
**Post date:** [October 21, 2021, 11:11pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Findexerror-tuple-index-out-of-range%2F10986%2F1 "2021-10-21T23:11:40Z")

</div>

> from transformers import AutoModelForMaskedLM  
> self.xlm\_roberta = AutoModelForMaskedLM.from\_pretrained(“xlm-roberta-base”)

When I changed the model like this, I got an error.  
I don’t really know what I can do to improve it.

> * * *
> 
> IndexError Traceback (most recent call last)  
> in   
> 4 print(f’FOLD: {fold}‘)  
> 5 print(’-'\*50)  
> ----\> 6 run(train, fold)
> 
> in run(data, fold)  
> 18 result\_dict = trainer.train(  
> 19 args, train\_dataloader,  
> —\> 20 epoch, result\_dict  
> 21 )  
> 22 torch.cuda.synchronize()
> 
> in train(self, args, train\_dataloader, epoch, result\_dict)  
> 32 outputs\_start, outputs\_end = self.model(  
> 33 input\_ids=input\_ids,  
> —\> 34 attention\_mask=attention\_mask,  
> 35 )  
> 36
> 
> /opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in \_call\_impl(self, \*input, \*\*kwargs)  
> 725 result = self.\_slow\_forward(\*input, \*\*kwargs)  
> 726 else:  
> → 727 result = self.forward(\*input, \*\*kwargs)  
> 728 for hook in itertools.chain(  
> 729 \_global\_forward\_hooks.values(),
> 
> in forward(self, input\_ids, attention\_mask)  
> 32  
> 33 sequence\_output = outputs[0]  
> —\> 34 pooled\_output = outputs[1]  
> 35  
> 36 # sequence\_output = self.dropout(sequence\_output)
> 
> /opt/conda/lib/python3.7/site-packages/transformers/file\_utils.py in **getitem** (self, k)  
> 1738 return inner\_dict[k]  
> 1739 else:  
> → 1740 return self.to\_tuple()[k]  
> 1741  
> 1742 def **setattr** (self, name, value):
> 
> IndexError: tuple index out of range

## Model code

> **[chaii QA - 5 Fold XLMRoberta Torch | Infer](https://www.kaggle.com/code/rhtsingh/chaii-qa-5-fold-xlmroberta-torch-infer)**
>
> Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources

## Model

> **[FacebookAI/xlm-roberta-base · Hugging Face](https://huggingface.co/FacebookAI/xlm-roberta-base)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.