You can deploy this model and start earning money today!

Keisyahsq/
JNLPBA_BERT2

Name: JNLPBA_BERT2
Availability: InStock

Views

No views yet

Keisyahsq/JNLPBA_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:

More information needed

More information needed

More information needed

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': 5790, '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

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.4149	0.3160	0.6803	0.7930	0.7324	0.8961	0
0.2225	0.2927	0.7081	0.8126	0.7568	0.9054	1
0.1842	0.3240	0.6925	0.8154	0.7490	0.9006	2
0.1576	0.3204	0.7136	0.8230	0.7644	0.9077	3
0.1372	0.3409	0.7096	0.8179	0.7599	0.9074	4
0.1200	0.3559	0.7130	0.8134	0.7599	0.9059	5
0.1064	0.3642	0.7111	0.8168	0.7603	0.9061	6