<!-- 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-finetuned-detests
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: 1.2565
- Accuracy: 0.8183
- F1-score: 0.7520
- Precision: 0.7432
- Recall: 0.7631
- Auc: 0.7631
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc |
|---|---|---|---|---|---|---|---|---|
| 0.421 | 1.0 | 174 | 0.4312 | 0.8151 | 0.6901 | 0.7477 | 0.6671 | 0.6671 |
| 0.2658 | 2.0 | 348 | 0.4703 | 0.8183 | 0.7586 | 0.7454 | 0.7784 | 0.7784 |
| 0.2854 | 3.0 | 522 | 0.4797 | 0.8134 | 0.7577 | 0.7421 | 0.7853 | 0.7853 |
| 0.146 | 4.0 | 696 | 0.5352 | 0.8429 | 0.7681 | 0.7794 | 0.7587 | 0.7587 |
| 0.1153 | 5.0 | 870 | 0.8277 | 0.8151 | 0.7498 | 0.7396 | 0.7636 | 0.7636 |
| 0.2146 | 6.0 | 1044 | 0.9727 | 0.8167 | 0.7537 | 0.7423 | 0.7697 | 0.7697 |
| 0.0714 | 7.0 | 1218 | 1.0588 | 0.8265 | 0.7615 | 0.7537 | 0.7710 | 0.7710 |
| 0.0571 | 8.0 | 1392 | 1.1897 | 0.8216 | 0.7553 | 0.7473 | 0.7653 | 0.7653 |
| 0.0243 | 9.0 | 1566 | 1.1598 | 0.8331 | 0.7625 | 0.7625 | 0.7625 | 0.7625 |
| 0.0934 | 10.0 | 1740 | 1.2565 | 0.8183 | 0.7520 | 0.7432 | 0.7631 | 0.7631 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
