|
--- |
|
license: mit |
|
base_model: VietAI/vit5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: sentiment_25_12 |
|
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. --> |
|
|
|
# sentiment_25_12 |
|
|
|
This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1668 |
|
- F1: 0.5760 |
|
- Accuracy: 0.8423 |
|
|
|
## 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: 80 |
|
- eval_batch_size: 80 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:| |
|
| 2.0596 | 0.24 | 100 | 0.2039 | 0.5316 | 0.8088 | |
|
| 0.1995 | 0.48 | 200 | 0.1781 | 0.5587 | 0.8332 | |
|
| 0.1887 | 0.72 | 300 | 0.1749 | 0.5600 | 0.8364 | |
|
| 0.1849 | 0.95 | 400 | 0.1703 | 0.5615 | 0.8376 | |
|
| 0.1791 | 1.19 | 500 | 0.1764 | 0.5615 | 0.8339 | |
|
| 0.1775 | 1.43 | 600 | 0.1687 | 0.5682 | 0.8420 | |
|
| 0.1794 | 1.67 | 700 | 0.1659 | 0.5665 | 0.8410 | |
|
| 0.1688 | 1.91 | 800 | 0.1710 | 0.5663 | 0.8414 | |
|
| 0.1766 | 2.15 | 900 | 0.1650 | 0.5665 | 0.8424 | |
|
| 0.1662 | 2.39 | 1000 | 0.1696 | 0.5750 | 0.8420 | |
|
| 0.1711 | 2.63 | 1100 | 0.1668 | 0.5718 | 0.8439 | |
|
| 0.1616 | 2.86 | 1200 | 0.1689 | 0.5680 | 0.8424 | |
|
| 0.166 | 3.1 | 1300 | 0.1667 | 0.5720 | 0.8437 | |
|
| 0.1634 | 3.34 | 1400 | 0.1654 | 0.5717 | 0.8401 | |
|
| 0.158 | 3.58 | 1500 | 0.1692 | 0.5664 | 0.8431 | |
|
| 0.1567 | 3.82 | 1600 | 0.1668 | 0.5727 | 0.8445 | |
|
| 0.165 | 4.06 | 1700 | 0.1661 | 0.5679 | 0.8439 | |
|
| 0.1577 | 4.3 | 1800 | 0.1672 | 0.5696 | 0.8433 | |
|
| 0.1563 | 4.53 | 1900 | 0.1666 | 0.5763 | 0.8435 | |
|
| 0.1554 | 4.77 | 2000 | 0.1667 | 0.5738 | 0.8424 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
