<!-- 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_delete
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: 0.8915
- Accuracy: 0.7
- F1: 0.7032
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0805 | 1.0 | 44 | 0.9603 | 0.61 | 0.5214 |
| 0.8688 | 2.0 | 88 | 0.7871 | 0.68 | 0.6492 |
| 0.7285 | 3.0 | 132 | 0.7653 | 0.71 | 0.7134 |
| 0.6103 | 4.0 | 176 | 0.7112 | 0.72 | 0.7197 |
| 0.5336 | 5.0 | 220 | 0.7593 | 0.7 | 0.7057 |
| 0.4561 | 6.0 | 264 | 0.7167 | 0.72 | 0.7210 |
| 0.4174 | 7.0 | 308 | 0.7432 | 0.73 | 0.7332 |
| 0.3602 | 8.0 | 352 | 0.8390 | 0.7 | 0.7032 |
| 0.2965 | 9.0 | 396 | 0.8819 | 0.69 | 0.6978 |
| 0.2937 | 10.0 | 440 | 0.8915 | 0.7 | 0.7032 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
