<!-- 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. -->
PhoBERT-cls-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: 0.4288
- Accuracy: 0.8812
- F1: 0.8812
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 |
|---|---|---|---|---|---|
| 0.5728 | 1.0 | 25 | 0.4112 | 0.8614 | 0.8590 |
| 0.2892 | 2.0 | 50 | 0.3444 | 0.8515 | 0.8511 |
| 0.1954 | 3.0 | 75 | 0.3638 | 0.8812 | 0.8816 |
| 0.1387 | 4.0 | 100 | 0.3591 | 0.8812 | 0.8806 |
| 0.1029 | 5.0 | 125 | 0.3809 | 0.8911 | 0.8908 |
| 0.053 | 6.0 | 150 | 0.4145 | 0.8911 | 0.8903 |
| 0.0527 | 7.0 | 175 | 0.4288 | 0.8812 | 0.8812 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
