metadata
license: mit
base_model: facebook/mbart-large-50
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-translation-en-ro
results: []
mbart-translation-en-ro
This model is a fine-tuned version of facebook/mbart-large-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7670
- Bleu: 24.6364
- Gen Len: 15.6295
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.8809 | 1.0 | 1250 | 1.8027 | 22.9582 | 14.6065 |
| 1.0076 | 2.0 | 2500 | 1.7670 | 24.6364 | 15.6295 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2