README.md

metadata

base_model:
  - FacebookAI/xlm-roberta-large
datasets:
  - google/xtreme
language:
  - en
library_name: transformers
license: mit
metrics:
  - f1
  - accuracy
  - precision
  - recall
pipeline_tag: token-classification
model-index:
  - name: xlm-roberta-large-panx-en
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: google/xtreme
          type: google/xtreme
          config: PAN-X.en
          split: validation
        metrics:
          - type: precision
            value: 0.834659287443791
            name: Precision
          - type: recall
            value: 0.852891276685989
            name: Recall
          - type: f1
            value: 0.8436767945176742
            name: F1
          - type: accuracy
            value: 0.9357306049468561
            name: Accuracy

XLM-RoBERTa-Large-PANX-WikiAnn-en

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the google/xtreme dataset (English split of the PAN-X). It achieves the following results on the evaluation set:

• Loss: 0.2569
• Precision: 0.8347
• Recall: 0.8529
• F1: 0.8437
• Accuracy: 0.9357

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1