<!-- 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. -->
bert-finetuned-ner
This model is a fine-tuned version of markusbayer/CySecBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6006
- Precision: 0.8664
- Recall: 0.8691
- F1: 0.8677
- Accuracy: 0.8546
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.6569 | 1.0 | 1690 | 0.6027 | 0.8427 | 0.8407 | 0.8417 | 0.8224 |
0.4821 | 2.0 | 3380 | 0.5506 | 0.8689 | 0.8663 | 0.8676 | 0.8549 |
0.3568 | 3.0 | 5070 | 0.6006 | 0.8664 | 0.8691 | 0.8677 | 0.8546 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0+cpu
- Datasets 2.11.0
- Tokenizers 0.13.2