testjpth / README.md
Shularp's picture
Update README.md
d0fc53c
metadata
license: cc-by-nc-4.0
tags:
  - generated_from_trainer
model-index:
  - name: testjpth
    results: []
language:
  - ja
  - th

testjpth

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset.

Model description

This is test version to translate Japanese to Thai. I use NLLB for this model.

Intended uses & limitations

This is just for the test concept of NLLB model

Training and evaluation data

The data was generated by other model. The dataset was split by intention to use in order to make the model understand some technical term.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3