xlm-roberta-base-ka-ner

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

• Loss: 0.2031
• Precision: 0.8506
• Recall: 0.8703
• F1: 0.8603
• Accuracy: 0.9425

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Metrics per category

{'LOC': {'precision': 0.8558191459670667, 'recall': 0.9074874223142941, 'f1': 0.8808962941683425, 'number': 16895}, 'ORG': {'precision': 0.7917612346799818, 'recall': 0.7510226049515608, 'f1': 0.7708540492763231, 'number': 9290}, 'PER': {'precision': 0.8896882494004796, 'recall': 0.9157884743188076, 'f1': 0.9025497076023392, 'number': 10533}, 'overall_precision': 0.8505682876839947, 'overall_recall': 0.8702816057519472, 'overall_f1': 0.8603120330609663, 'overall_accuracy': 0.9424682155180856}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0