|
--- |
|
base_model: IAmSkyDra/BARTBana_v4 |
|
library_name: transformers |
|
license: mit |
|
metrics: |
|
- sacrebleu |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: BARTBana_Translation_InsertSwap_v0 |
|
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_InsertSwap_v0 |
|
|
|
This model is a fine-tuned version of [IAmSkyDra/BARTBana_v4](https://huggingface.co/IAmSkyDra/BARTBana_v4) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0372 |
|
- Sacrebleu: 10.1870 |
|
|
|
## 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: 100 |
|
- eval_batch_size: 100 |
|
- 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: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:| |
|
| 0.1353 | 1.0 | 13718 | 0.0911 | 9.0612 | |
|
| 0.0672 | 2.0 | 27436 | 0.0456 | 9.9443 | |
|
| 0.0529 | 3.0 | 41154 | 0.0372 | 10.1870 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.1 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
