apriadiazriel/bert-cased-jnlpba

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

• Train Loss: 0.0851
• Validation Loss: 0.2221
• Precision: 0.6744
• Recall: 0.7808
• F1: 0.7237
• Accuracy: 0.9371
• 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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5795, '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	Validation Loss	Precision	Recall	F1	Accuracy	Epoch
0.2424	0.1998	0.6507	0.7606	0.7014	0.9322	0
0.1426	0.1975	0.6613	0.7832	0.7171	0.9364	1
0.1166	0.2051	0.6527	0.7847	0.7127	0.9353	2
0.0984	0.2108	0.6750	0.7811	0.7242	0.9378	3
0.0851	0.2221	0.6744	0.7808	0.7237	0.9371	4

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Datasets 3.3.2
• Tokenizers 0.21.0