sohidalg/bert-finetuned-ner

This model is a fine-tuned version of bert-base-cased on the conll2003 dataset.

Intended uses & limitations

Named Entity Recognition, (NER).

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': 2634, '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: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
0.1793	0.0663	0
0.0458	0.0555	1
0.0266	0.0556	2

Framework versions

• Transformers 4.47.1
• TensorFlow 2.17.1
• Datasets 3.2.0
• Tokenizers 0.21.0