metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: PhoBERT-train-aug_insert_w2v
results: []
PhoBERT-train-aug_insert_w2v
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: 1.2218
- Accuracy: 0.71
- F1: 0.7185
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 |
|---|---|---|---|---|---|
| 0.861 | 1.0 | 85 | 0.7003 | 0.71 | 0.6826 |
| 0.532 | 2.0 | 170 | 0.6556 | 0.73 | 0.7305 |
| 0.361 | 3.0 | 255 | 0.7729 | 0.74 | 0.7346 |
| 0.2421 | 4.0 | 340 | 0.9271 | 0.65 | 0.6591 |
| 0.177 | 5.0 | 425 | 1.0259 | 0.71 | 0.7199 |
| 0.1242 | 6.0 | 510 | 1.2122 | 0.68 | 0.6905 |
| 0.093 | 7.0 | 595 | 1.2365 | 0.68 | 0.6889 |
| 0.0886 | 8.0 | 680 | 1.2218 | 0.71 | 0.7185 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3