metadata
library_name: transformers
license: apache-2.0
base_model: cisco-ai/SecureBERT2.0-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SecureBERT2.0-ner
results: []
SecureBERT2.0-ner
This model is a fine-tuned version of cisco-ai/SecureBERT2.0-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2745
- Precision: 0.5641
- Recall: 0.5361
- F1: 0.5497
- Accuracy: 0.8981
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 487 | 0.2967 | 0.4305 | 0.3045 | 0.3567 | 0.8696 |
| 0.4569 | 2.0 | 974 | 0.2485 | 0.4620 | 0.4440 | 0.4528 | 0.8852 |
| 0.2305 | 3.0 | 1461 | 0.2569 | 0.5296 | 0.5140 | 0.5217 | 0.8887 |
| 0.1465 | 4.0 | 1948 | 0.2527 | 0.5571 | 0.5197 | 0.5378 | 0.8974 |
| 0.089 | 5.0 | 2435 | 0.2745 | 0.5641 | 0.5361 | 0.5497 | 0.8981 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.2
- Tokenizers 0.22.1