metadata
base_model: vinai/phobert-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model
results: []
model
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: 0.1373
- Accuracy: 0.9709
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 95 | 1.0978 | 0.8201 |
| No log | 2.0 | 190 | 0.5250 | 0.9392 |
| No log | 3.0 | 285 | 0.3076 | 0.9418 |
| No log | 4.0 | 380 | 0.2149 | 0.9471 |
| No log | 5.0 | 475 | 0.2237 | 0.9497 |
| 0.6823 | 6.0 | 570 | 0.1904 | 0.9630 |
| 0.6823 | 7.0 | 665 | 0.1716 | 0.9656 |
| 0.6823 | 8.0 | 760 | 0.1373 | 0.9709 |
| 0.6823 | 9.0 | 855 | 0.1403 | 0.9683 |
| 0.6823 | 10.0 | 950 | 0.1374 | 0.9709 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0