gte-large-en-v1.5-based-ft-prompt-injection-detection-241205Weighted-17
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: 0.7014
- F1: 0.0
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 |
|---|---|---|---|---|
| 0.452 | 0.2527 | 100 | 0.2348 | 0.9039 |
| 0.2009 | 0.5054 | 200 | 0.1794 | 0.9343 |
| 0.1595 | 0.7581 | 300 | 0.1470 | 0.9452 |
| 0.1523 | 1.0107 | 400 | 0.1182 | 0.9566 |
| 0.1072 | 1.2634 | 500 | 0.1256 | 0.9545 |
| 0.1113 | 1.5161 | 600 | 0.1319 | 0.9531 |
| 0.1168 | 1.7688 | 700 | 0.1450 | 0.9438 |
| 0.1129 | 2.0215 | 800 | 0.1331 | 0.9564 |
| 0.2379 | 2.2742 | 900 | 0.6936 | 0.7087 |
| 0.7027 | 2.5268 | 1000 | 0.6899 | 0.7087 |
| 0.6948 | 2.7795 | 1100 | 0.6918 | 0.7087 |
| 0.675 | 3.0322 | 1200 | 0.7413 | 0.0 |
| 0.6709 | 3.2849 | 1300 | 0.6972 | 0.0 |
| 0.6698 | 3.5376 | 1400 | 0.7014 | 0.0 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 36
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-17
Base model
Alibaba-NLP/gte-large-en-v1.5