Keisyahsq/BC2GM_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: 0.0186
• Validation Loss: 0.1193
• Train Precision: 0.8395
• Train Recall: 0.8646
• Train F1: 0.8518
• Train Accuracy: 0.9696
• 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': 3900, '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
0.1732	0.1023	0.7706	0.8272	0.7979	0.9604	0
0.0881	0.0869	0.8154	0.8485	0.8316	0.9663	1
0.0601	0.0933	0.8274	0.8591	0.8429	0.9686	2
0.0433	0.1004	0.8503	0.8512	0.8507	0.9697	3
0.0305	0.1066	0.8332	0.8640	0.8483	0.9687	4
0.0230	0.1094	0.8430	0.8625	0.8526	0.9695	5
0.0186	0.1193	0.8395	0.8646	0.8518	0.9696	6

Framework versions

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