README.md

---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-de-en
tags:
- generated_from_trainer
- medical
model-index:
- name: opus-mt-de-en-OPUS_Medical_German_to_English
  results: []
datasets:
- ahazeemi/opus-medical-en-de
language:
- en
- de
metrics:
- bleu
- rouge
pipeline_tag: translation
---

# opus-mt-de-en-OPUS_Medical_German_to_English

This model is a fine-tuned version of [Helsinki-NLP/opus-mt-de-en](https://huggingface.co/Helsinki-NLP/opus-mt-de-en).

### Model description

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/Medical%20-%20German%20to%20English/OPUS_Medical_German_to_English_OPUS_Translation_Project.ipynb

### Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology.

### Training and evaluation data

Dataset Source: https://huggingface.co/datasets/ahazeemi/opus-medical-en-de


#### Histogram of German Input Word Counts

![German Word Count of Input Text](https://github.com/DunnBC22/NLP_Projects/raw/main/Machine%20Translation/Medical%20-%20German%20to%20English/Images/Histogram%20of%20German%20Input%20Lengths.png)

#### Histogram of English Input Word Counts

![English Word Count of Input Text](https://github.com/DunnBC22/NLP_Projects/raw/main/Machine%20Translation/Medical%20-%20German%20to%20English/Images/Histogram%20of%20English%20Input%20Lengths.png)


## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

- eval_loss: 0.8723
- eval_bleu: 53.88120
- eval_rouge:
  - rouge1: 0.7664
  - rouge2: 0.6284
  - rougeL: 0.7370
  - rougeLsum: 0.7370
 
* The training results values are rounded to the nearest ten-thousandth.

### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3