tmnam20's picture
Upload README.md with huggingface_hub
7869f91 verified
metadata
language:
  - en
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
  - generated_from_trainer
datasets:
  - tmnam20/VieGLUE
metrics:
  - accuracy
  - f1
model-index:
  - name: mdeberta-v3-base-qqp-100
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: tmnam20/VieGLUE/QQP
          type: tmnam20/VieGLUE
          config: qqp
          split: validation
          args: qqp
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8987880286915657
          - name: F1
            type: f1
            value: 0.8654655444502892

mdeberta-v3-base-qqp-100

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the tmnam20/VieGLUE/QQP dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2790
  • Accuracy: 0.8988
  • F1: 0.8655
  • Combined Score: 0.8821

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 32
  • eval_batch_size: 16
  • seed: 100
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Combined Score
0.3099 0.44 5000 0.2921 0.8751 0.8326 0.8539
0.269 0.88 10000 0.2732 0.8820 0.8378 0.8599
0.2421 1.32 15000 0.2795 0.8894 0.8520 0.8707
0.2198 1.76 20000 0.2674 0.8937 0.8566 0.8751
0.188 2.2 25000 0.2778 0.8964 0.8602 0.8783
0.1916 2.64 30000 0.2861 0.8977 0.8636 0.8807

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0