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: 0.4424
- Accuracy: 0.8383
- F1: 0.8222
- Precision: 0.8189
- Recall: 0.8260
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5757 | 1.0 | 105 | 0.5760 | 0.6948 | 0.5676 | 0.6774 | 0.5811 |
| 0.4861 | 2.0 | 210 | 0.4837 | 0.7663 | 0.7328 | 0.7410 | 0.7272 |
| 0.4106 | 3.0 | 315 | 0.4200 | 0.8033 | 0.7800 | 0.7817 | 0.7785 |
| 0.3777 | 4.0 | 420 | 0.3928 | 0.8200 | 0.7953 | 0.8033 | 0.7893 |
| 0.2995 | 5.0 | 525 | 0.3835 | 0.8331 | 0.8187 | 0.8129 | 0.8272 |
| 0.3012 | 6.0 | 630 | 0.3786 | 0.8404 | 0.8222 | 0.8227 | 0.8217 |
| 0.26 | 7.0 | 735 | 0.3827 | 0.8399 | 0.8265 | 0.8202 | 0.8361 |
| 0.2388 | 8.0 | 840 | 0.4340 | 0.8346 | 0.8139 | 0.8180 | 0.8104 |
| 0.2092 | 9.0 | 945 | 0.4377 | 0.8388 | 0.8237 | 0.8192 | 0.8294 |
| 0.1957 | 10.0 | 1050 | 0.4424 | 0.8383 | 0.8222 | 0.8189 | 0.8260 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1