Keisyahsq/JNLPBA_BERT16

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: 0.0830
• Validation Loss: 0.4179
• Train Precision: 0.6965
• Train Recall: 0.8246
• Train F1: 0.7551
• Train Accuracy: 0.9034
• 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': 11590, '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
0.3702	0.3196	0.6597	0.8000	0.7231	0.8965	0
0.2097	0.2841	0.7092	0.8131	0.7576	0.9055	1
0.1710	0.3149	0.6923	0.8345	0.7568	0.9050	2
0.1422	0.3281	0.7026	0.8191	0.7564	0.9037	3
0.1174	0.3543	0.7064	0.8170	0.7577	0.9057	4
0.0989	0.3698	0.7098	0.8153	0.7589	0.9051	5
0.0830	0.4179	0.6965	0.8246	0.7551	0.9034	6

Framework versions

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