---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ar
tags:
- translation
- generated_from_trainer
model-index:
- name: Text2Gloss_ar
  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. -->

# Text2Gloss_ar

This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0336
- Word Bleu: 96.3751
- Char Bleu: 98.5195

## 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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Word Bleu | Char Bleu |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:---------:|
| 3.0445        | 1.0   | 190  | 1.0130          | 14.7298   | 31.5277   |
| 0.863         | 2.0   | 380  | 0.4001          | 52.2907   | 67.3129   |
| 0.4146        | 3.0   | 570  | 0.1912          | 76.9208   | 85.7130   |
| 0.2205        | 4.0   | 760  | 0.0918          | 89.7162   | 94.7752   |
| 0.1296        | 5.0   | 950  | 0.0617          | 92.7357   | 96.6210   |
| 0.0868        | 6.0   | 1140 | 0.0522          | 93.6404   | 97.0249   |
| 0.0641        | 7.0   | 1330 | 0.0364          | 95.8783   | 98.4617   |
| 0.047         | 8.0   | 1520 | 0.0359          | 95.9872   | 98.4311   |
| 0.0386        | 9.0   | 1710 | 0.0318          | 96.5580   | 98.6017   |
| 0.0316        | 10.0  | 1900 | 0.0336          | 96.3751   | 98.5195   |


### Framework versions

- Transformers 4.42.4
- Pytorch 1.12.0+cu102
- Datasets 2.21.0
- Tokenizers 0.19.1