LovenOO/distilBERT_with_preprocessing

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.2890
• Validation Loss: 0.6104
• Train Accuracy: 0.8264
• Epoch: 5

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': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2545, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6308	0.6631	0.8136	0
0.4767	0.6222	0.8264	1
0.3731	0.6148	0.8308	2
0.3117	0.6104	0.8264	3
0.2875	0.6104	0.8264	4
0.2890	0.6104	0.8264	5

Framework versions

• Transformers 4.24.0
• TensorFlow 2.13.0
• Datasets 2.14.2
• Tokenizers 0.11.0