gustavokpc/IC_sexto

This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0832
• Train Accuracy: 0.9695
• Train F1 M: 0.5509
• Train Precision M: 0.4007
• Train Recall M: 0.9444
• Validation Loss: 0.2387
• Validation Accuracy: 0.9248
• Validation F1 M: 0.5604
• Validation Precision M: 0.4074
• Validation Recall M: 0.9461
• Epoch: 4

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: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3790, '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}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train F1 M	Train Precision M	Train Recall M	Validation Loss	Validation Accuracy	Validation F1 M	Validation Precision M	Validation Recall M	Epoch
0.3898	0.8294	0.3411	0.2894	0.4810	0.2440	0.8984	0.5087	0.3814	0.8079	0
0.2070	0.9228	0.4927	0.3723	0.7869	0.1911	0.9268	0.5222	0.3853	0.8520	1
0.1392	0.9467	0.5266	0.3881	0.8670	0.2310	0.9057	0.5617	0.4162	0.9092	2
0.1136	0.9570	0.5387	0.3946	0.9100	0.2265	0.9228	0.5653	0.4119	0.9501	3
0.0832	0.9695	0.5509	0.4007	0.9444	0.2387	0.9248	0.5604	0.4074	0.9461	4

Framework versions

• Transformers 4.34.1
• TensorFlow 2.10.0
• Datasets 2.14.5
• Tokenizers 0.14.1