distilbert-base-uncased-nvidia-aegis-v2-augmented
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2818
- Accuracy: 0.8756
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 |
|---|---|---|---|---|
| 0.8393 | 1.0 | 8402 | 0.3430 | 0.8395 |
| 0.4610 | 2.0 | 16804 | 0.2815 | 0.8758 |
| 0.2319 | 3.0 | 25206 | 0.3292 | 0.8862 |
| 0.3144 | 4.0 | 33608 | 0.3165 | 0.8944 |
| 0.1178 | 5.0 | 42010 | 0.3211 | 0.9026 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2