gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-41
This model is a fine-tuned version of Alibaba-NLP/gte-large-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1900
- F1: 0.9527
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
0.4552 | 0.2527 | 100 | 0.2210 | 0.9100 |
0.1965 | 0.5054 | 200 | 0.1912 | 0.9298 |
0.1597 | 0.7581 | 300 | 0.1320 | 0.9520 |
0.1509 | 1.0107 | 400 | 0.1212 | 0.9574 |
0.1062 | 1.2634 | 500 | 0.1348 | 0.9500 |
0.1109 | 1.5161 | 600 | 0.1812 | 0.9462 |
0.1172 | 1.7688 | 700 | 0.1335 | 0.9530 |
0.1127 | 2.0215 | 800 | 0.1414 | 0.9564 |
0.0754 | 2.2742 | 900 | 0.1359 | 0.9553 |
0.0837 | 2.5268 | 1000 | 0.1182 | 0.9603 |
0.093 | 2.7795 | 1100 | 0.1459 | 0.9511 |
0.0926 | 3.0322 | 1200 | 0.1386 | 0.9564 |
0.0669 | 3.2849 | 1300 | 0.1504 | 0.9584 |
0.0683 | 3.5376 | 1400 | 0.1682 | 0.9487 |
0.07 | 3.7903 | 1500 | 0.1494 | 0.9498 |
0.0663 | 4.0430 | 1600 | 0.1934 | 0.9497 |
0.0471 | 4.2956 | 1700 | 0.2087 | 0.9500 |
0.0546 | 4.5483 | 1800 | 0.1867 | 0.9477 |
0.1081 | 4.8010 | 1900 | 0.1720 | 0.9579 |
0.0505 | 5.0537 | 2000 | 0.1900 | 0.9527 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 10
Inference API (serverless) does not yet support model repos that contain custom code.
Model tree for J1N2/gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-41
Base model
Alibaba-NLP/gte-large-en-v1.5