<!-- 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_insert_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: 0.9449
- Accuracy: 0.75
- F1: 0.7539
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 |
|---|---|---|---|---|---|
| 1.0882 | 1.0 | 87 | 1.0321 | 0.51 | 0.4420 |
| 0.8914 | 2.0 | 174 | 0.7622 | 0.61 | 0.5759 |
| 0.6966 | 3.0 | 261 | 0.7336 | 0.71 | 0.7090 |
| 0.5329 | 4.0 | 348 | 0.7699 | 0.74 | 0.7427 |
| 0.4203 | 5.0 | 435 | 0.7875 | 0.75 | 0.7536 |
| 0.3473 | 6.0 | 522 | 0.8840 | 0.74 | 0.7431 |
| 0.2737 | 7.0 | 609 | 0.9115 | 0.75 | 0.7526 |
| 0.218 | 8.0 | 696 | 0.9449 | 0.75 | 0.7539 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
