ne-en
This model is a fine-tuned version of Helsinki-NLP/opus-mt-hi-en on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.3494
- Validation Loss: 1.7265
- Epoch: 4
Model description
More information needed
Intended uses & limitations
More information needed
BLEU Score
The model achieves a BLEU score of 28.66 on the test
split of the BeebekBhz/ne-en
dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
2.2912 | 1.9530 | 0 |
1.8413 | 1.8206 | 1 |
1.6270 | 1.7661 | 2 |
1.4746 | 1.7402 | 3 |
1.3494 | 1.7265 | 4 |
Framework versions
- Transformers 4.48.3
- TensorFlow 2.18.0
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 41
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for BeebekBhz/ne-en
Base model
Helsinki-NLP/opus-mt-hi-en