cyber_bert
This model is a fine-tuned version of google-bert/bert-base-multilingual-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4264
- Accuracy: 0.8159
- F1: 0.8047
- Precision: 0.7981
- Recall: 0.8230
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 |
---|---|---|---|---|---|---|---|
0.4532 | 1.0 | 144 | 0.4371 | 0.7939 | 0.7843 | 0.7803 | 0.8082 |
0.3505 | 2.0 | 288 | 0.3934 | 0.8179 | 0.8035 | 0.7973 | 0.8139 |
0.3378 | 3.0 | 432 | 0.4232 | 0.8065 | 0.7978 | 0.7940 | 0.8240 |
0.2601 | 4.0 | 576 | 0.4264 | 0.8159 | 0.8047 | 0.7981 | 0.8230 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 6