---
library_name: transformers
license: apache-2.0
base_model: google/electra-large-discriminator
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-hybrid-detector
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# deberta-v3-hybrid-detector

This model is a fine-tuned version of [google/electra-large-discriminator](https://huggingface.co/google/electra-large-discriminator) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0564
- Accuracy: 0.9654

## 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: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0926        | 0.125 | 1000 | 0.0443          | 0.9446   |
| 0.0565        | 0.25  | 2000 | 0.0480          | 0.9251   |
| 0.0442        | 0.375 | 3000 | 0.2126          | 0.8871   |
| 0.0383        | 0.5   | 4000 | 0.0716          | 0.9479   |
| 0.0332        | 0.625 | 5000 | 0.2383          | 0.8774   |
| 0.0253        | 0.75  | 6000 | 0.0347          | 0.9706   |
| 0.0168        | 0.875 | 7000 | 0.0347          | 0.9795   |
| 0.0117        | 1.0   | 8000 | 0.0564          | 0.9654   |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.8.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1