metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: cyber_distilbert
results: []
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: 0.4491
- Accuracy: 0.7971
- F1: 0.7871
- Precision: 0.7824
- Recall: 0.8099
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: 1e-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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4835 | 1.0 | 144 | 0.4918 | 0.7543 | 0.7486 | 0.7571 | 0.7859 |
| 0.4014 | 2.0 | 288 | 0.4116 | 0.7992 | 0.7831 | 0.7774 | 0.7927 |
| 0.3788 | 3.0 | 432 | 0.4453 | 0.7872 | 0.7777 | 0.7746 | 0.8027 |
| 0.3943 | 4.0 | 576 | 0.4264 | 0.8018 | 0.7903 | 0.7843 | 0.8090 |
| 0.3518 | 5.0 | 720 | 0.4491 | 0.7971 | 0.7871 | 0.7824 | 0.8099 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1