hate_speech_classifier

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

• Train Loss: 0.0710
• Train Accuracy: 0.9765
• Train Precision: 0.9207
• Train Recall: 0.9921
• Validation Loss: 0.3637
• Validation Accuracy: 0.9016
• Validation Precision: 0.8507
• Validation Recall: 0.9371
• 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 3720, '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, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Precision	Train Recall	Validation Loss	Validation Accuracy	Validation Precision	Validation Recall	Epoch
0.1715	0.9374	0.8596	0.9650	0.3057	0.9024	0.7826	0.9463	0
0.1203	0.9572	0.8813	0.9846	0.3223	0.9034	0.8117	0.9455	1
0.0710	0.9765	0.9207	0.9921	0.3637	0.9016	0.8507	0.9371	2

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Tokenizers 0.21.0