You can deploy this model and start earning money today!

oskarandrsson/
mt-no-sv-finetuned

Name: mt-no-sv-finetuned
Availability: InStock

generated_from_trainer

apache-2.0

endpoints_compatible

Views

No views yet

mt-no-sv-finetuned

This model is a fine-tuned version of 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

oskarandrsson/mt-no-sv-finetuned

mt-no-sv-finetuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

oskarandrsson/
mt-no-sv-finetuned