theatticusproject / cuad Goto Github PK

Can you share code to fine-tune the fine-tuned roberta model? Just a simple example containing one contract with all the required features is enough.

In the CUAD paper you show the chart below. Can you share the precision numbers that correspond to each clause? That would be useful for comparing against other models.

I couldn't locate them in the provided documentation, do you mind pointing or linking to them in README?

We provide checkpoints for three of the best models fine-tuned on CUAD: RoBERTa-base (~100M parameters), RoBERTa-large (~300M parameters), and DeBERTa-xlarge (~900M parameters).

Thanks so much for open sourcing this dataset, looking forward to using it! I would love if you added it to Hugging Face's Datasets to make it even more accessible and discoverable for folks!

The "--predict_file ./data/test.json" file is labeled with questions and answers, and it's passed directly into predictions = compute_predictions_logits() for predictions in train.py.

If I want to use your model to do predictions on my own dataset, do I also need to label it in the same json format? Doesn't that defeat the purpose? Let me know if I am misunderstanding, but shouldn't the model predict on unlabeled, raw text file?

Thanks!

Hi

When using the Deberta model for predictions, it takes more than an hour for one document (85 page document). Is there any way to reduce the time taken?, please advise on this.
Thanks in advance.

When I run the training script, I ran into an instance of 'std::runtime_error'
what(): NCCL Error 1: unhandled cuda error
./run.sh

This happens every time in the Evaluation step of the train.py script - after the 'convert squad examples to features' step completes successfully and right after 'Evaluating: 0%' is printed.

I have made sure torch can pick up the cuda info:

print(torch.cuda.is_available())
True

Hello,
The step to convert squad examples to features is very slow on my machine:48 cores + GPU. The tqdm estimates 24 hours to finish. Is it normal? Thanks!

convert squad examples to features: 4%|██ | 865/22450 [20:16<24:52:42, 4.15s/it]

Could you teach me a license of your code and attach license file to your repository?
Thank you.

When "Creating features from dataset file at .", this code consumes too much memory (I have a 48G machine).

This makes me can not run this code. (I guess this needs a 128G machine)

Is it possible to fix this problem? Thx.

Please share the code if available to get inference on standard paragraph and question.

Could you upload the script that was used to generate the train_separate_questions.json and test.json files?

Could you please create Google Colab to Run The Model?
Thanks @TheAtticusProject

Right now I am able to get start logits and end logits from the model output. but these logits contain features and examples.
How can I get the start and end index for answers so, that I can mark those on the context in the form of a bounding box.

@TheAtticusProject

When "Creating features from dataset file at .", this code consumes too much memory (I have a 110G machine).

This makes me can not run this code.
Is it possible to fix this problem?
can you please guide me on what GPU specification should I use for training? @TheAtticusProject @IsCoelacanth @wangdsh

First at all, thanks for this amazing dataset and for the pretrained models. Would it be possible to push your models to the huggingface model's hub https://huggingface.co/models ? I can do it too but I think it would give the models more legitimacy if they came from your account