Keisyahsq/NCBI_BERT2

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: 0.0081
• Validation Loss: 0.0888
• Train Precision: 0.8281
• Train Recall: 0.8908
• Train F1: 0.8583
• Train Accuracy: 0.9823
• Epoch: 6

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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1690, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.1958	0.0731	0.7798	0.7967	0.7882	0.9769	0
0.0562	0.0681	0.8049	0.8796	0.8406	0.9812	1
0.0313	0.0745	0.7967	0.8664	0.8301	0.9797	2
0.0213	0.0753	0.8135	0.8954	0.8525	0.9816	3
0.0139	0.0813	0.8285	0.8836	0.8551	0.9826	4
0.0107	0.0824	0.8282	0.8849	0.8556	0.9825	5
0.0081	0.0888	0.8281	0.8908	0.8583	0.9823	6

Framework versions

• Transformers 4.31.0
• TensorFlow 2.10.1
• Datasets 3.0.0
• Tokenizers 0.13.3