metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-Final_Mixed-aug_insert_BERT-1
results: []
PhoBERT-Final_Mixed-aug_insert_BERT-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: 1.2876
- Accuracy: 0.66
- F1: 0.6737
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 |
|---|---|---|---|---|---|
| 0.8758 | 1.0 | 87 | 0.7479 | 0.67 | 0.6552 |
| 0.5767 | 2.0 | 174 | 0.6555 | 0.74 | 0.7384 |
| 0.4132 | 3.0 | 261 | 0.7503 | 0.75 | 0.7532 |
| 0.2927 | 4.0 | 348 | 0.8208 | 0.68 | 0.6890 |
| 0.2246 | 5.0 | 435 | 1.0222 | 0.68 | 0.6927 |
| 0.1536 | 6.0 | 522 | 1.1675 | 0.67 | 0.6839 |
| 0.1218 | 7.0 | 609 | 1.2362 | 0.66 | 0.6737 |
| 0.1142 | 8.0 | 696 | 1.2876 | 0.66 | 0.6737 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3