metadata
base_model: facebook/mbart-large-50
library_name: transformers
license: mit
tags:
- generated_from_trainer
model-index:
- name: fine-tune-mBart-ar-en
results: []
fine-tune-mBart-ar-en
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: 0.3951
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Step | Training Loss | Validation Loss | Bleu |
|---|---|---|---|
| 1000 2.189400 2.368187 10.742858 | |||
| 2000 1.745500 2.349487 12.255348 | |||
| 3000 1.389300 2.395577 11.255426 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0