cyber_distilbert
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4481
- Accuracy: 0.8023
- F1: 0.7912
- Precision: 0.7854
- Recall: 0.8109
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.4557 | 1.0 | 144 | 0.4442 | 0.7851 | 0.7752 | 0.7718 | 0.7993 |
0.3629 | 2.0 | 288 | 0.3937 | 0.8164 | 0.7998 | 0.7950 | 0.8065 |
0.3234 | 3.0 | 432 | 0.4456 | 0.7971 | 0.7873 | 0.7828 | 0.8106 |
0.3167 | 4.0 | 576 | 0.4481 | 0.8023 | 0.7912 | 0.7854 | 0.8109 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 7