Modelpublic

apriadiazriel/bert-base-bc2gm-ner

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes6downloads

Model Card

apriadiazriel/bert-base-bc2gm-ner

This model is a fine-tuned version of bert-base-uncased on the BC2GM Corpus. It achieves the following results on the evaluation set:

—Train Loss: 0.0035
—Validation Loss: 0.1569
—Precision: 0.8494
—Recall: 0.8766
—F1: 0.8628
—Accuracy: 0.9714
—Epoch: 9

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': 'AdamWeightDecay', 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-05, 'decaysteps': 15620, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecay_rate': 0.01}
—training_precision: float32

Training results

Train Loss	Validation Loss	Precision	Recall	F1	Accuracy	Epoch
0.1451	0.0924	0.8182	0.8184	0.8183	0.9647	0
0.0718	0.0859	0.8272	0.8595	0.8431	0.9687	1
0.0444	0.1031	0.8597	0.8478	0.8537	0.9697	2
0.0270	0.1078	0.8459	0.8633	0.8545	0.9697	3
0.0179	0.1165	0.8556	0.8646	0.8601	0.9708	4
0.0133	0.1281	0.8514	0.8701	0.8606	0.9712	5
0.0083	0.1469	0.8293	0.8889	0.8581	0.9691	6
0.0059	0.1568	0.8450	0.8808	0.8625	0.9709	7
0.0045	0.1540	0.8519	0.8760	0.8638	0.9714	8
0.0035	0.1569	0.8494	0.8766	0.8628	0.9714	9

Framework versions

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