hogger32/xlm-roberta-base-finetuned-ner

This model is a fine-tuned version of hogger32/xlm-roberta-base-finetuned-ner on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0463
• Validation Loss: 0.1634
• Train Precision: 0.8956
• Train Recall: 0.9286
• Train F1: 0.9118
• Train Accuracy: 0.9710
• Epoch: 5

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', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1320, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.0603	0.1571	0.8868	0.9156	0.9010	0.9709	0
0.0696	0.1486	0.9013	0.9091	0.9052	0.9666	1
0.0446	0.1723	0.8789	0.9264	0.9020	0.9651	2
0.0483	0.1400	0.8864	0.9286	0.9070	0.9702	3
0.0403	0.1511	0.9099	0.9177	0.9138	0.9708	4
0.0463	0.1634	0.8956	0.9286	0.9118	0.9710	5

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2