<!-- 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-New_VietNam-aug_backtranslation-1
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: 1.8120
- Accuracy: 0.71
- F1: 0.7138
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 |
|---|---|---|---|---|---|
| 0.4667 | 1.0 | 86 | 1.0350 | 0.71 | 0.7195 |
| 0.3031 | 2.0 | 172 | 1.3877 | 0.72 | 0.7270 |
| 0.2394 | 3.0 | 258 | 1.4133 | 0.7 | 0.7051 |
| 0.1781 | 4.0 | 344 | 1.4430 | 0.69 | 0.6914 |
| 0.1565 | 5.0 | 430 | 1.5583 | 0.71 | 0.7173 |
| 0.0964 | 6.0 | 516 | 1.8780 | 0.69 | 0.6938 |
| 0.0779 | 7.0 | 602 | 1.8000 | 0.72 | 0.7256 |
| 0.0846 | 8.0 | 688 | 1.8120 | 0.71 | 0.7138 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
