finetuned-kde4-pt-to-ca-2
This model is a fine-tuned version of Helsinki-NLP/opus-mt-pt-ca on the open_subtitles dataset. It achieves the following results on the evaluation set:
- Loss: 0.0943
- Bleu: 35.7188
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: 3
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for tarsssss/finetuned-kde4-pt-to-ca-2
Base model
Helsinki-NLP/opus-mt-pt-caDataset used to train tarsssss/finetuned-kde4-pt-to-ca-2
Evaluation results
- Bleu on open_subtitlesself-reported35.719