Giter VIP home page Giter VIP logo

Comments (4)

joey234 avatar joey234 commented on May 26, 2024

Hi, thank you for your interest in our project.

This error means that you did not have a trained JointBERT-CRF model first before training the JointIDSF model.

Can you check if the directory JointBERT-CRF_PhoBERTencoder/3e-5/0.6/100 is created before the training process of JointIDSF begin?

I just double-check the training script (.sh) files, please try pulling the repo and run again and see if there are still any error.

from jointidsf.

nguyenvlm avatar nguyenvlm commented on May 26, 2024

Thanks for your quick response.

I have re-cloned the repo and still have the same issue. The XLM-R one seems to be fine, but the PhoBERT one always yields the error. The directory JointBERT-CRF_PhoBERTencoder/3e-5/0.6/100 was not created before the training process.

To give you more details, the code was executed on Google Colab:

%%shell
git clone https://github.com/VinAIResearch/JointIDSF.git
cd JointIDSF/
pip3 install -r requirements.txt

During the pip installing process I got the following "errors" (they were warnings I suppose):

ERROR: torchvision 0.10.0+cu102 has requirement torch==1.9.0, but you'll have torch 1.6.0 which is incompatible.
ERROR: torchtext 0.10.0 has requirement torch==1.9.0, but you'll have torch 1.6.0 which is incompatible.
ERROR: tensorflow 2.2.0 has requirement tensorboard<2.3.0,>=2.2.0, but you'll have tensorboard 2.5.0 which is incompatible.
Installing collected packages: torch, tokenizers, sacremoses, transformers, seqeval, pytorch-crf, gast, tensorflow-estimator, h5py, tensorflow, sentencepiece
  Found existing installation: torch 1.9.0+cu102
    Uninstalling torch-1.9.0+cu102:
      Successfully uninstalled torch-1.9.0+cu102
  Found existing installation: gast 0.4.0
    Uninstalling gast-0.4.0:
      Successfully uninstalled gast-0.4.0
  Found existing installation: tensorflow-estimator 2.5.0
    Uninstalling tensorflow-estimator-2.5.0:
      Successfully uninstalled tensorflow-estimator-2.5.0
  Found existing installation: h5py 3.1.0
    Uninstalling h5py-3.1.0:
      Successfully uninstalled h5py-3.1.0
  Found existing installation: tensorflow 2.5.0
    Uninstalling tensorflow-2.5.0:
      Successfully uninstalled tensorflow-2.5.0
Successfully installed gast-0.3.3 h5py-2.10.0 pytorch-crf-0.7.2 sacremoses-0.0.45 sentencepiece-0.1.96 seqeval-0.0.12 tensorflow-2.2.0 tensorflow-estimator-2.2.0 tokenizers-0.9.4 torch-1.6.0 transformers-4.1.1

After the pip installing process, I executed the following colab cell:

%%shell
cd /content/JointIDSF/
./run_jointIDSF_PhoBERTencoder.sh

and got the error output.

from jointidsf.

joey234 avatar joey234 commented on May 26, 2024

I see, try setting --gpu_id to 0 in the file run_jointBERT-CRF_PhoBERTencoder.sh. It should be ok now.

from jointidsf.

nguyenvlm avatar nguyenvlm commented on May 26, 2024

Thank you. It works now. The issue has gone.

from jointidsf.

Related Issues (8)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.