|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: IAmSkyDra/BARTBana_v5 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- sacrebleu |
|
model-index: |
|
- name: BARTBana_Translation_v5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# BARTBana_Translation_v5 |
|
|
|
This model is a fine-tuned version of [IAmSkyDra/BARTBana_v5](https://huggingface.co/IAmSkyDra/BARTBana_v5) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5602 |
|
- Sacrebleu: 7.0962 |
|
|
|
## 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: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:| |
|
| 0.8121 | 1.0 | 742 | 0.7206 | 1.9030 | |
|
| 0.7484 | 2.0 | 1484 | 0.6697 | 2.9685 | |
|
| 0.6761 | 3.0 | 2226 | 0.6374 | 4.0287 | |
|
| 0.6557 | 4.0 | 2968 | 0.6162 | 4.8115 | |
|
| 0.6185 | 5.0 | 3710 | 0.6006 | 5.2849 | |
|
| 0.6033 | 6.0 | 4452 | 0.5889 | 5.7585 | |
|
| 0.573 | 7.0 | 5194 | 0.5807 | 6.1391 | |
|
| 0.5573 | 8.0 | 5936 | 0.5758 | 6.3215 | |
|
| 0.5491 | 9.0 | 6678 | 0.5688 | 6.4682 | |
|
| 0.534 | 10.0 | 7420 | 0.5653 | 6.7433 | |
|
| 0.5204 | 11.0 | 8162 | 0.5630 | 6.8459 | |
|
| 0.5144 | 12.0 | 8904 | 0.5620 | 6.9725 | |
|
| 0.5069 | 13.0 | 9646 | 0.5602 | 7.0593 | |
|
| 0.5021 | 14.0 | 10388 | 0.5596 | 7.0546 | |
|
| 0.4929 | 15.0 | 11130 | 0.5602 | 7.0962 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.1 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
