Roberta-NER-Multi-Language

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

• Train Loss: 0.0773
• Train Accuracy: 0.9830
• Validation Loss: 0.0993
• Validation Accuracy: 0.9827
• Epoch: 0

Model description

More information needed

Intended uses & limitations

More information needed

Label_Map

{0: 0, 'I-DATE': 1, 'B-PERSON': 2, 'B-MONEY': 3, 'I-ORG': 4, 'B-PRODUCT': 5, 'I-PERSON': 6, 'B-NORP': 7, 'I-GPE': 8, 'B-PERCENT': 9, 'B-ORG': 10, 'B-TIME': 11, 'B-CARDINAL': 12, 'B-EVENT': 13, 'I-WORK_OF_ART': 14, 'B-QUANTITY': 15, 'B-WORK_OF_ART': 16, 'B-GPE': 17, 'B-LAW': 18, 'B-LANGUAGE': 19, 'O': 20, 'I-FAC': 21, 'B-ORDINAL': 22, 'B-FAC': 23, 'B-DATE': 24, 'I-EVENT': 25, 'B-LOC': 26}

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.0773	0.9830	0.0993	0.9827	0

Framework versions

• Transformers 4.46.3
• TensorFlow 2.17.1
• Tokenizers 0.20.3