|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-base |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: pijarcandra22/NMTBaliIndoBART |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# pijarcandra22/NMTBaliIndoBART |
|
|
|
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 5.4694 |
|
- Validation Loss: 6.0100 |
|
- Epoch: 16 |
|
|
|
## 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 | |
|
|:----------:|:---------------:|:-----:| |
|
| 9.3368 | 5.6757 | 0 | |
|
| 5.5627 | 5.5987 | 1 | |
|
| 5.5311 | 5.5419 | 2 | |
|
| 5.5152 | 5.5201 | 3 | |
|
| 5.5005 | 5.6477 | 4 | |
|
| 5.4704 | 5.5914 | 5 | |
|
| 5.4610 | 6.0922 | 6 | |
|
| 5.4584 | 5.7137 | 7 | |
|
| 5.4528 | 5.8658 | 8 | |
|
| 5.4820 | 5.5628 | 9 | |
|
| 5.4874 | 5.5309 | 10 | |
|
| 5.4917 | 5.7595 | 11 | |
|
| 5.4898 | 5.7333 | 12 | |
|
| 5.4833 | 5.6789 | 13 | |
|
| 5.4767 | 5.9588 | 14 | |
|
| 5.4883 | 5.9895 | 15 | |
|
| 5.4694 | 6.0100 | 16 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
