metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-aug_replace_synonym-train
results: []
PhoBERT-aug_replace_synonym-train
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: 0.9138
- Accuracy: 0.7
- F1: 0.7075
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 |
|---|---|---|---|---|---|
| 1.0279 | 1.0 | 44 | 0.8516 | 0.72 | 0.6966 |
| 0.7329 | 2.0 | 88 | 0.7172 | 0.74 | 0.7274 |
| 0.5587 | 3.0 | 132 | 0.7033 | 0.73 | 0.7274 |
| 0.4356 | 4.0 | 176 | 0.7519 | 0.7 | 0.7046 |
| 0.3429 | 5.0 | 220 | 0.7372 | 0.71 | 0.7159 |
| 0.27 | 6.0 | 264 | 0.8128 | 0.7 | 0.6991 |
| 0.2487 | 7.0 | 308 | 0.8904 | 0.73 | 0.7314 |
| 0.2058 | 8.0 | 352 | 0.9138 | 0.7 | 0.7075 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3