Hugging Face's logo

oskarandrsson
/
mt-hr-sv-finetuned

Translation
Transformers
PyTorch
Croatian
Swedish
marian
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Community
1
mt-hr-sv-finetuned / README.md
lbourdois's picture
lbourdois
Add multilingual to the language tag
659b69c
preview code
|
raw
history blame
1.33 kB
metadata
language:
  - hr
  - sv
  - multilingual
license: apache-2.0
tags:
  - generated_from_trainer
  - translation
model-index:
  - name: mt-hr-sv-finetuned
    results: []

mt-hr-sv-finetuned

This model is a fine-tuned version of Helsinki-NLP/opus-mt-hr-sv on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.9565
  • eval_bleu: 49.8248
  • eval_runtime: 873.8605
  • eval_samples_per_second: 16.982
  • eval_steps_per_second: 4.246
  • epoch: 5.0
  • step: 27825

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: 10
  • mixed_precision_training: Native AMP

Framework versions

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