metadata
base_model: vinai/phobert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-cls-detail-in-Non_OCR
results: []
PhoBERT-cls-detail-in-Non_OCR
This model is a fine-tuned version of vinai/phobert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2965
- Accuracy: 0.95
- F1: 0.9359
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.5312 | 1.0 | 25 | 1.2681 | 0.55 | 0.4060 |
| 1.1478 | 2.0 | 50 | 0.8709 | 0.82 | 0.7465 |
| 0.7779 | 3.0 | 75 | 0.5259 | 0.92 | 0.8928 |
| 0.528 | 4.0 | 100 | 0.3918 | 0.92 | 0.8928 |
| 0.4236 | 5.0 | 125 | 0.3363 | 0.94 | 0.9254 |
| 0.3641 | 6.0 | 150 | 0.3035 | 0.95 | 0.9359 |
| 0.3356 | 7.0 | 175 | 0.2965 | 0.95 | 0.9359 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1