metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-cls-OCR
results: []
PhoBERT-cls-OCR
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: 0.5749
- Accuracy: 0.8515
- F1: 0.8504
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 |
|---|---|---|---|---|---|
| 0.5828 | 1.0 | 25 | 0.4474 | 0.8119 | 0.8093 |
| 0.3067 | 2.0 | 50 | 0.3924 | 0.8218 | 0.8199 |
| 0.1806 | 3.0 | 75 | 0.3979 | 0.8416 | 0.8399 |
| 0.1043 | 4.0 | 100 | 0.4770 | 0.8317 | 0.8294 |
| 0.0688 | 5.0 | 125 | 0.5007 | 0.8614 | 0.8607 |
| 0.0406 | 6.0 | 150 | 0.5332 | 0.8614 | 0.8614 |
| 0.0387 | 7.0 | 175 | 0.5748 | 0.8515 | 0.8504 |
| 0.0328 | 8.0 | 200 | 0.5749 | 0.8515 | 0.8504 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1