<!-- 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_replace_synonym-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: 2.3309
- Accuracy: 0.63
- F1: 0.6393
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 |
|---|---|---|---|---|---|
| 0.3738 | 1.0 | 86 | 1.0460 | 0.69 | 0.6960 |
| 0.2198 | 2.0 | 172 | 1.6273 | 0.67 | 0.6759 |
| 0.1523 | 3.0 | 258 | 2.0692 | 0.66 | 0.6651 |
| 0.1015 | 4.0 | 344 | 2.0397 | 0.68 | 0.6891 |
| 0.073 | 5.0 | 430 | 2.0420 | 0.69 | 0.7014 |
| 0.0509 | 6.0 | 516 | 2.3116 | 0.68 | 0.6907 |
| 0.0549 | 7.0 | 602 | 2.3421 | 0.65 | 0.6560 |
| 0.0549 | 8.0 | 688 | 2.3309 | 0.63 | 0.6393 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
