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: 0.4646
- Accuracy: 0.8273
- F1: 0.8125
- Precision: 0.8068
- Recall: 0.8207
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 |
---|---|---|---|---|---|---|---|
0.3747 | 1.0 | 277 | 0.4398 | 0.7981 | 0.7899 | 0.7874 | 0.8177 |
0.2971 | 2.0 | 554 | 0.4022 | 0.8226 | 0.8101 | 0.8031 | 0.8241 |
0.2659 | 3.0 | 831 | 0.4262 | 0.8258 | 0.8135 | 0.8065 | 0.8280 |
0.2387 | 4.0 | 1108 | 0.4502 | 0.8320 | 0.8168 | 0.8118 | 0.8235 |
0.268 | 5.0 | 1385 | 0.4646 | 0.8273 | 0.8125 | 0.8068 | 0.8207 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1