mbart-large-50-finetuned-en-to-ba
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8138
- Bleu: 6.0837
- Gen Len: 46.235
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: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 12000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.9435 | 0.6949 | 1000 | 2.6296 | 3.6886 | 47.431 |
| 1.2417 | 1.3899 | 2000 | 2.5577 | 4.294 | 52.199 |
| 1.0716 | 2.0848 | 3000 | 2.5397 | 5.2872 | 50.81 |
| 0.9341 | 2.7797 | 4000 | 2.5230 | 5.6413 | 46.144 |
| 0.843 | 3.4746 | 5000 | 2.5927 | 5.891 | 47.693 |
| 0.7785 | 4.1696 | 6000 | 2.6120 | 6.477 | 45.289 |
| 0.7117 | 4.8645 | 7000 | 2.6530 | 6.1367 | 45.901 |
| 0.6505 | 5.5594 | 8000 | 2.7041 | 6.0327 | 46.667 |
| 0.6209 | 6.2543 | 9000 | 2.7524 | 6.4298 | 46.083 |
| 0.5857 | 6.9493 | 10000 | 2.7564 | 6.2065 | 47.203 |
| 0.5484 | 7.6442 | 11000 | 2.7948 | 6.5806 | 46.407 |
| 0.5317 | 8.3391 | 12000 | 2.8138 | 6.0837 | 46.235 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for 21uyennt/mbart-large-50-finetuned-en-to-ba
Base model
facebook/mbart-large-50-many-to-many-mmt