metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_keras_callback
model-index:
- name: pijarcandra22/BartIndo2Bali
results: []
pijarcandra22/BartIndo2Bali
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: 1.8837
- Validation Loss: 2.2181
- Epoch: 13
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 |
|---|---|---|
| 4.3767 | 3.6194 | 0 |
| 3.5364 | 3.1996 | 1 |
| 3.1525 | 2.9458 | 2 |
| 2.8777 | 2.8118 | 3 |
| 2.6993 | 2.6979 | 4 |
| 2.5550 | 2.6071 | 5 |
| 2.4536 | 2.5362 | 6 |
| 2.3338 | 2.4572 | 7 |
| 2.2394 | 2.3878 | 8 |
| 2.1466 | 2.3692 | 9 |
| 2.0795 | 2.3189 | 10 |
| 2.0061 | 2.2674 | 11 |
| 1.9321 | 2.2393 | 12 |
| 1.8837 | 2.2181 | 13 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0