electra-base-discriminator-nvidia-aegis-v2-augmented
This model is a fine-tuned version of google/electra-base-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2955
- Accuracy: 0.9017
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 |
|---|---|---|---|---|
| 0.8266 | 1.0 | 8402 | 0.3551 | 0.8340 |
| 0.4659 | 2.0 | 16804 | 0.2982 | 0.8757 |
| 0.3200 | 3.0 | 25206 | 0.3303 | 0.8842 |
| 0.4265 | 4.0 | 33608 | 0.2955 | 0.9020 |
| 0.2627 | 5.0 | 42010 | 0.3568 | 0.9011 |
| 0.2254 | 6.0 | 50412 | 0.3222 | 0.9062 |
| 0.2324 | 7.0 | 58814 | 0.3780 | 0.9037 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2