metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-Final_Mixed-aug_insert_synonym
results: []
PhoBERT-Final_Mixed-aug_insert_synonym
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: 1.2173
- Accuracy: 0.72
- F1: 0.7208
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 |
|---|---|---|---|---|---|
| 0.8905 | 1.0 | 88 | 0.7446 | 0.67 | 0.6565 |
| 0.6277 | 2.0 | 176 | 0.7272 | 0.72 | 0.7163 |
| 0.4506 | 3.0 | 264 | 0.7680 | 0.7 | 0.6957 |
| 0.3032 | 4.0 | 352 | 0.8468 | 0.73 | 0.7307 |
| 0.2046 | 5.0 | 440 | 0.9995 | 0.7 | 0.7011 |
| 0.1487 | 6.0 | 528 | 1.1278 | 0.72 | 0.7157 |
| 0.1103 | 7.0 | 616 | 1.1927 | 0.71 | 0.7097 |
| 0.0985 | 8.0 | 704 | 1.2173 | 0.72 | 0.7208 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3