|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: vinai/bartpho-syllable |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: BARTBana_v1 |
|
|
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_v1 |
|
|
|
|
|
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.5525 |
|
|
|
|
|
## 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: 8 |
|
|
- eval_batch_size: 8 |
|
|
- 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: 10 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 4.2284 | 1.0 | 1316 | 3.1527 | |
|
|
| 2.6988 | 2.0 | 2632 | 2.3799 | |
|
|
| 2.38 | 3.0 | 3948 | 2.0462 | |
|
|
| 2.0879 | 4.0 | 5264 | 1.8895 | |
|
|
| 1.9391 | 5.0 | 6580 | 1.7817 | |
|
|
| 1.8423 | 6.0 | 7896 | 1.7480 | |
|
|
| 1.7697 | 7.0 | 9212 | 1.6467 | |
|
|
| 1.6992 | 8.0 | 10528 | 1.5939 | |
|
|
| 1.6668 | 9.0 | 11844 | 1.5594 | |
|
|
| 1.632 | 10.0 | 13160 | 1.5200 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
