LovenOO/distilBERT_without_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: 0.1466
• Validation Loss: 0.3625
• Train Precision: 0.8491
• Train Recall: 0.8642
• Train F1: 0.8544
• Train Accuracy: 0.8906
• 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': 2565, '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 Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.8177	0.4723	0.8407	0.7879	0.7948	0.8575	0
0.3642	0.3777	0.8666	0.8315	0.8465	0.8847	1
0.2734	0.3804	0.8466	0.8563	0.8471	0.8872	2
0.2020	0.3704	0.8526	0.8663	0.8551	0.8896	3
0.1638	0.3625	0.8491	0.8642	0.8544	0.8906	4
0.1466	0.3625	0.8491	0.8642	0.8544	0.8906	5

Framework versions

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