|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: vinai/bartpho-word |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: fine-tuning_BARTPho |
|
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. --> |
|
|
|
# fine-tuning_BARTPho |
|
|
|
This model is a fine-tuned version of [vinai/bartpho-word](https://huggingface.co/vinai/bartpho-word) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1876 |
|
- Accuracy: 0.014 |
|
- F1: 0.0011 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Use 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 3.7202 | 1.0 | 125 | 1.3840 | 0.016 | 0.0018 | |
|
| 1.3287 | 2.0 | 250 | 1.2517 | 0.014 | 0.0011 | |
|
| 1.2451 | 3.0 | 375 | 1.2197 | 0.016 | 0.0015 | |
|
| 1.2059 | 4.0 | 500 | 1.2077 | 0.014 | 0.0011 | |
|
| 1.105 | 5.0 | 625 | 1.2053 | 0.014 | 0.0011 | |
|
| 1.1054 | 6.0 | 750 | 1.1893 | 0.018 | 0.0015 | |
|
| 1.1207 | 7.0 | 875 | 1.1881 | 0.022 | 0.0045 | |
|
| 1.1011 | 8.0 | 1000 | 1.1857 | 0.016 | 0.0025 | |
|
| 1.0578 | 9.0 | 1125 | 1.1877 | 0.016 | 0.0031 | |
|
| 1.0836 | 10.0 | 1250 | 1.1876 | 0.014 | 0.0011 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
