metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_keras_callback
model-index:
- name: pijarcandra22/NMTIndoBaliBART
results: []
pijarcandra22/NMTIndoBaliBART
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.5217
- Validation Loss: 5.5513
- Epoch: 12
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': 0.02, '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 |
|---|---|---|
| 9.7885 | 5.6003 | 0 |
| 5.5737 | 5.5523 | 1 |
| 5.5346 | 5.5361 | 2 |
| 5.5189 | 5.5283 | 3 |
| 5.5149 | 5.5252 | 4 |
| 5.5123 | 5.5233 | 5 |
| 5.5116 | 5.5485 | 6 |
| 5.5095 | 5.5314 | 7 |
| 5.5120 | 5.5569 | 8 |
| 5.5137 | 5.5239 | 9 |
| 5.5170 | 5.5289 | 10 |
| 5.5180 | 5.5298 | 11 |
| 5.5217 | 5.5513 | 12 |
Framework versions
- Transformers 4.40.2
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1