---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: TestHelsinkimulEnJpTh0
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# TestHelsinkimulEnJpTh0

This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-mul](https://huggingface.co/Helsinki-NLP/opus-mt-en-mul) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6882

## Model description

This model use Marian Helsinki Model to translate English to Japanese or Thai, it is to test that the model can test 2 languages simentously.
To use this translation  use ">>jpn<<{english sentence}" or ">>tha<<{english sentence}"  the model is very poor because of using very few sample.

## Intended uses & limitations

I hope you will not too trust this model to works, for now.

## Training and evaluation data

Generated data from Chat GPT by some medical concepts

## 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: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.4665        | 1.0   | 4846  | 0.8669          |
| 0.1461        | 2.0   | 9692  | 0.7631          |
| 0.419         | 3.0   | 14538 | 0.7144          |
| 0.1456        | 4.0   | 19384 | 0.6867          |
| 0.2308        | 5.0   | 24230 | 0.6882          |


### Framework versions

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