---
license: apache-2.0
language:
- sv
- no
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mt-no-sv-finetuned
  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. -->

# mt-no-sv-finetuned

This model is a fine-tuned version of [Helsinki-NLP/opus-mt-no-sv](https://huggingface.co/Helsinki-NLP/opus-mt-no-sv) on the None dataset.
It achieves the following results on the Tatoeba.Nor.Swe evaluation set:
- Loss: 0.5130
- Bleu: 66.4015

## 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-06
- train_batch_size: 24
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu    |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 1.085         | 1.0   | 10268 | 0.5365          | 65.9489 |
| 1.0258        | 2.0   | 20536 | 0.5221          | 66.0704 |
| 0.9783        | 3.0   | 30804 | 0.5147          | 66.4690 |
| 0.9578        | 4.0   | 41072 | 0.5130          | 66.4015 |


### Framework versions

- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1