xlm-roberta-large-finetuned-ner

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the conll2002 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0882
• Precision: 0.8638
• Recall: 0.8814
• F1: 0.8725
• Accuracy: 0.9794

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:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0718	1.0	1041	0.1022	0.8368	0.8612	0.8488	0.9764
0.0398	2.0	2082	0.0882	0.8638	0.8814	0.8725	0.9794

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1