<!-- 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-Balance_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: 0.9985
- Accuracy: 0.72
- F1: 0.7249
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 |
---|---|---|---|---|---|
1.0573 | 1.0 | 87 | 0.8704 | 0.64 | 0.5908 |
0.8411 | 2.0 | 174 | 0.7557 | 0.67 | 0.6079 |
0.6874 | 3.0 | 261 | 0.6533 | 0.72 | 0.7112 |
0.5116 | 4.0 | 348 | 0.6770 | 0.73 | 0.7338 |
0.4243 | 5.0 | 435 | 0.7311 | 0.74 | 0.7466 |
0.3378 | 6.0 | 522 | 0.8615 | 0.72 | 0.7180 |
0.2496 | 7.0 | 609 | 0.9281 | 0.73 | 0.7332 |
0.2269 | 8.0 | 696 | 0.9985 | 0.72 | 0.7249 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3