english_kumaoni-mbart_large
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: 3.8143
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.1837 | 1.0 | 1133 | 5.0117 |
| 4.78 | 2.0 | 2266 | 4.6802 |
| 4.5691 | 3.0 | 3399 | 4.4787 |
| 4.3752 | 4.0 | 4532 | 4.3266 |
| 4.2656 | 5.0 | 5665 | 4.2151 |
| 4.1741 | 6.0 | 6798 | 4.1338 |
| 4.0978 | 7.0 | 7931 | 4.0474 |
| 3.9998 | 8.0 | 9064 | 3.9952 |
| 3.9682 | 9.0 | 10197 | 3.9317 |
| 3.9121 | 10.0 | 11330 | 3.9082 |
| 3.8589 | 11.0 | 12463 | 3.8674 |
| 3.8396 | 12.0 | 13596 | 3.8455 |
| 3.8058 | 13.0 | 14729 | 3.8335 |
| 3.7847 | 14.0 | 15862 | 3.8232 |
| 3.7661 | 15.0 | 16995 | 3.8143 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 64
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for sourabsb/english_kumaoni-mbart_large
Base model
facebook/mbart-large-50-many-to-many-mmt