<!-- 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. -->
roberta-finetuned-solvencia-v1
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: 0.4141
- Accuracy: 0.8919
- F1: 0.8919
- Precision: 0.8919
- Recall: 0.8919
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 333 | 0.3781 | 0.8544 | 0.8544 | 0.8544 | 0.8544 |
| 0.4429 | 2.0 | 666 | 0.3295 | 0.8679 | 0.8679 | 0.8679 | 0.8679 |
| 0.4429 | 3.0 | 999 | 0.3664 | 0.8784 | 0.8784 | 0.8784 | 0.8784 |
| 0.3512 | 4.0 | 1332 | 0.4602 | 0.8649 | 0.8649 | 0.8649 | 0.8649 |
| 0.2975 | 5.0 | 1665 | 0.4721 | 0.8889 | 0.8889 | 0.8889 | 0.8889 |
| 0.2975 | 6.0 | 1998 | 0.4141 | 0.8919 | 0.8919 | 0.8919 | 0.8919 |
| 0.2499 | 7.0 | 2331 | 0.4054 | 0.8889 | 0.8889 | 0.8889 | 0.8889 |
| 0.2132 | 8.0 | 2664 | 0.4878 | 0.8829 | 0.8829 | 0.8829 | 0.8829 |
| 0.2132 | 9.0 | 2997 | 0.4867 | 0.8904 | 0.8904 | 0.8904 | 0.8904 |
| 0.1812 | 10.0 | 3330 | 0.5339 | 0.8889 | 0.8889 | 0.8889 | 0.8889 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.9.1
- Datasets 1.18.4
- Tokenizers 0.11.6
