metadata
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_keras_callback
model-index:
- name: ai-detector-deberta
results: []
ai-detector-deberta
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0031
- Train Accuracy: 0.9994
- Validation Loss: 0.0242
- Validation Accuracy: 0.9924
- Train Lr: 1e-07
- Epoch: 2
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:
- optimizer: {'name': 'RMSprop', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': 100, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-07, 'rho': 0.9, 'momentum': 0.0, 'epsilon': 1e-07, 'centered': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Train Lr | Epoch |
|---|---|---|---|---|---|
| 0.0707 | 0.9694 | 0.0260 | 0.9903 | 1e-05 | 0 |
| 0.0032 | 0.9993 | 0.0383 | 0.9882 | 1e-06 | 1 |
| 0.0031 | 0.9994 | 0.0242 | 0.9924 | 1e-07 | 2 |
Framework versions
- Transformers 4.41.1
- TensorFlow 2.15.0
- Tokenizers 0.19.1