|
--- |
|
library_name: transformers |
|
license: agpl-3.0 |
|
base_model: vinai/phobert-base-v2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: PhoBert_Lexical_CITA |
|
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. --> |
|
|
|
# PhoBert_Lexical_CITA |
|
|
|
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6736 |
|
- Accuracy: 0.783 |
|
- F1: 0.7825 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.5393 | 1.0 | 250 | 0.4700 | 0.7695 | 0.7680 | |
|
| 0.4508 | 2.0 | 500 | 0.4686 | 0.7735 | 0.7735 | |
|
| 0.3951 | 3.0 | 750 | 0.4711 | 0.78 | 0.7800 | |
|
| 0.3402 | 4.0 | 1000 | 0.4895 | 0.7845 | 0.7846 | |
|
| 0.2947 | 5.0 | 1250 | 0.5293 | 0.782 | 0.7815 | |
|
| 0.2516 | 6.0 | 1500 | 0.5567 | 0.7775 | 0.7773 | |
|
| 0.2199 | 7.0 | 1750 | 0.5993 | 0.787 | 0.7857 | |
|
| 0.192 | 8.0 | 2000 | 0.6361 | 0.7825 | 0.7816 | |
|
| 0.1705 | 9.0 | 2250 | 0.6498 | 0.7835 | 0.7834 | |
|
| 0.1526 | 10.0 | 2500 | 0.6736 | 0.783 | 0.7825 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.21.0 |
|
|
