<!-- 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_CSIC-Anomaly
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0135
- Accuracy: 0.9978
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 |
|---|---|---|---|---|
| 0.0994 | 1.0 | 1094 | 0.0327 | 0.9902 |
| 0.032 | 2.0 | 2188 | 0.0233 | 0.9938 |
| 0.0229 | 3.0 | 3282 | 0.0209 | 0.995 |
| 0.0176 | 4.0 | 4376 | 0.0190 | 0.995 |
| 0.0171 | 5.0 | 5470 | 0.0261 | 0.9948 |
| 0.0127 | 6.0 | 6564 | 0.0190 | 0.996 |
| 0.0111 | 7.0 | 7658 | 0.0154 | 0.9968 |
| 0.0072 | 8.0 | 8752 | 0.0202 | 0.9972 |
| 0.0032 | 9.0 | 9846 | 0.0122 | 0.998 |
| 0.0026 | 10.0 | 10940 | 0.0125 | 0.998 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
