electricidad-small-discriminator-finetuned-clasificacion-texto-suicida
This model is a fine-tuned version of mrm8488/electricidad-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0458
- Accuracy: 0.9916
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
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Validation Loss | Accuracy |
|---|---|---|---|
| 0.161100 | 1.0 | 0.133057 | 0.952718 |
| 0.134500 | 2.0 | 0.110966 | 0.960804 |
| 0.108500 | 3.0 | 0.086417 | 0.970835 |
| 0.099400 | 4.0 | 0.073618 | 0.974856 |
| 0.090500 | 5.0 | 0.065231 | 0.979629 |
| 0.080700 | 6.0 | 0.060849 | 0.982324 |
| 0.069200 | 7.0 | 0.054718 | 0.986125 |
| 0.060400 | 8.0 | 0.051153 | 0.985948 |
| 0.048200 | 9.0 | 0.045747 | 0.989748 |
| 0.045500 | 10.0 | 0.049992 | 0.988069 |
| 0.043400 | 11.0 | 0.046325 | 0.990234 |
| 0.034300 | 12.0 | 0.050746 | 0.989792 |
| 0.032900 | 13.0 | 0.043434 | 0.991737 |
| 0.028400 | 14.0 | 0.045003 | 0.991869 |
| 0.022300 | 15.0 | 0.045819 | 0.991648 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6