nli-MiniLM2-L6-H768-nvidia-aegis-v1-augmented
This model is a fine-tuned version of cross-encoder/nli-MiniLM2-L6-H768 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2039
- Accuracy: 0.9498
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6661 | 1.0 | 3024 | 0.2987 | 0.8732 |
| 0.5838 | 2.0 | 6048 | 0.2087 | 0.9201 |
| 0.1355 | 3.0 | 9072 | 0.2036 | 0.9331 |
| 0.2975 | 4.0 | 12096 | 0.2070 | 0.9408 |
| 0.1735 | 5.0 | 15120 | 0.2035 | 0.9503 |
| 0.0610 | 6.0 | 18144 | 0.2243 | 0.9468 |
| 0.0986 | 7.0 | 21168 | 0.2293 | 0.9520 |
| 0.0088 | 8.0 | 24192 | 0.2552 | 0.9525 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2