Hugging Face's logo

raptorkwok
/
bart-base-cantonese

PyTorch
JAX
TensorBoard
bart
Generated from Trainer
Model card Files Metrics Community
bart-base-cantonese / README.md
raptorkwok's picture
raptorkwok
update model card README.md
64d477c
preview code
|
raw
history blame contribute delete
1.2 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bart-base-cantonese
    results: []

bart-base-cantonese

This model is a fine-tuned version of notebooks/cantonese/bart-base-chinese on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4687
  • Accuracy: 0.7968

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1.0

Training results

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.4.1+cu121
  • Datasets 2.19.1
  • Tokenizers 0.13.3