metadata
license: mit
base_model: facebook/mbart-large-50
tags:
- generated_from_keras_callback
model-index:
- name: mbart-finetuned-hindi-3012
results: []
mbart-finetuned-hindi-3012
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:
- Train Loss: 0.4568
- Validation Loss: 1.0632
- Epoch: 3
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:
- 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 |
|---|---|---|
| 0.9287 | 0.9910 | 0 |
| 0.7548 | 0.9679 | 1 |
| 0.5955 | 1.0150 | 2 |
| 0.4568 | 1.0632 | 3 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.0
- Tokenizers 0.15.0