metadata
license: mit
base_model: MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: cyber_deberta
results: []
cyber_deberta
This model is a fine-tuned version of MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4223
- Accuracy: 0.8320
- F1: 0.8216
- Precision: 0.8144
- Recall: 0.8401
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 |
---|---|---|---|---|---|---|---|
0.4368 | 1.0 | 144 | 0.4103 | 0.8117 | 0.8002 | 0.7936 | 0.8180 |
0.336 | 2.0 | 288 | 0.3805 | 0.8315 | 0.8186 | 0.8117 | 0.8305 |
0.3028 | 3.0 | 432 | 0.4287 | 0.8268 | 0.8186 | 0.8132 | 0.8442 |
0.248 | 4.0 | 576 | 0.4223 | 0.8320 | 0.8216 | 0.8144 | 0.8401 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1