metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-Final_Mixed-aug_delete
results: []
PhoBERT-Final_Mixed-aug_delete
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: 1.2677
- Accuracy: 0.7
- F1: 0.6952
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: 42
- 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 |
|---|---|---|---|---|---|
| 0.9293 | 1.0 | 88 | 0.7964 | 0.67 | 0.6494 |
| 0.6574 | 2.0 | 176 | 0.7447 | 0.69 | 0.6842 |
| 0.4468 | 3.0 | 264 | 0.8170 | 0.7 | 0.6904 |
| 0.2964 | 4.0 | 352 | 0.8311 | 0.68 | 0.6751 |
| 0.1996 | 5.0 | 440 | 1.0457 | 0.7 | 0.6962 |
| 0.1475 | 6.0 | 528 | 1.1385 | 0.71 | 0.7026 |
| 0.0796 | 7.0 | 616 | 1.2282 | 0.7 | 0.6922 |
| 0.0785 | 8.0 | 704 | 1.2677 | 0.7 | 0.6952 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3