<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlm-roberta-base-Final_VietNam-aug_replace_BERT
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8161
- Accuracy: 0.73
- F1: 0.7384
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 |
|---|---|---|---|---|---|
| 1.0522 | 1.0 | 87 | 0.9422 | 0.46 | 0.3717 |
| 0.8991 | 2.0 | 174 | 0.8059 | 0.6 | 0.5244 |
| 0.8082 | 3.0 | 261 | 0.7385 | 0.69 | 0.6744 |
| 0.6733 | 4.0 | 348 | 0.7667 | 0.73 | 0.7347 |
| 0.5768 | 5.0 | 435 | 0.6833 | 0.73 | 0.7351 |
| 0.5068 | 6.0 | 522 | 0.7653 | 0.71 | 0.7202 |
| 0.4404 | 7.0 | 609 | 0.8258 | 0.7 | 0.7119 |
| 0.3644 | 8.0 | 696 | 0.8161 | 0.73 | 0.7384 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
