<!-- 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_backtranslation
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: 1.0702
- Accuracy: 0.78
- F1: 0.7814
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 |
|---|---|---|---|---|---|
| 1.0167 | 1.0 | 86 | 0.7405 | 0.64 | 0.6009 |
| 0.6718 | 2.0 | 172 | 0.7008 | 0.73 | 0.7270 |
| 0.5117 | 3.0 | 258 | 0.8917 | 0.68 | 0.6842 |
| 0.3846 | 4.0 | 344 | 0.7874 | 0.75 | 0.7549 |
| 0.2693 | 5.0 | 430 | 0.8838 | 0.74 | 0.7422 |
| 0.2077 | 6.0 | 516 | 0.9699 | 0.77 | 0.7721 |
| 0.1657 | 7.0 | 602 | 1.0567 | 0.76 | 0.7653 |
| 0.1749 | 8.0 | 688 | 1.0702 | 0.78 | 0.7814 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
