metadata
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: distilbert-base-cased
model-index:
- name: ai-detector-distilbert
results: []
ai-detector-distilbert
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0079
- Train Accuracy: 0.9983
- Validation Loss: 0.0156
- Validation Accuracy: 0.9958
- 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 |
|---|---|---|---|---|---|
| 0.0921 | 0.9652 | 0.0141 | 0.9963 | 1e-05 | 0 |
| 0.0098 | 0.9974 | 0.0178 | 0.9956 | 1e-06 | 1 |
| 0.0079 | 0.9983 | 0.0156 | 0.9958 | 1e-07 | 2 |
Framework versions
- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2