metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-Final_Mixed-aug_delete-1
results: []
PhoBERT-Final_Mixed-aug_delete-1
This model is a fine-tuned version of vinai/phobert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2856
- Accuracy: 0.67
- F1: 0.6793
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: 16
- eval_batch_size: 16
- seed: 41
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8888 | 1.0 | 87 | 0.7251 | 0.66 | 0.6234 |
| 0.5843 | 2.0 | 174 | 0.6946 | 0.72 | 0.7261 |
| 0.3911 | 3.0 | 261 | 0.7680 | 0.68 | 0.6867 |
| 0.2678 | 4.0 | 348 | 0.8719 | 0.69 | 0.7012 |
| 0.1904 | 5.0 | 435 | 1.0179 | 0.7 | 0.7063 |
| 0.1384 | 6.0 | 522 | 1.1530 | 0.72 | 0.7264 |
| 0.1254 | 7.0 | 609 | 1.2665 | 0.69 | 0.6976 |
| 0.0992 | 8.0 | 696 | 1.2856 | 0.67 | 0.6793 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3