zh-za-theme
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: 2.0812
- Sacrebleu: 19.5320
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: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|---|---|---|---|---|
| 0.7090 | 1.0 | 1678 | 2.0409 | 16.4536 |
| 0.4013 | 2.0 | 3356 | 2.0482 | 18.7315 |
| 0.2852 | 3.0 | 5034 | 2.0812 | 19.5320 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for FiveC/zh-za-theme
Base model
facebook/mbart-large-50-many-to-many-mmt