metadata

library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: xlm-roberta-base-finetuned-panx-de-fr-en-it
    results:
      - task:
          type: token-classification
        dataset:
          name: google/xtreme
          type: google/xtreme
        metrics:
          - name: f1
            type: f1
            value: 0.838
datasets:
  - google/xtreme
language:
  - de
  - fr
  - en
  - it
pipeline_tag: token-classification

xlm-roberta-base-finetuned-panx-de-fr-en-it

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

Loss: 0.2148
F1: 0.8380

Model description

This model is fine-tuned for Named Entity Recognition (NER) in German, French, English, and Italian. It identifies entities like persons, organizations, locations, etc...

Intended uses & limitations

More information needed

How to Use

from transformers import pipeline

# Load the NER pipeline
model_name = "avanishd/xlm-roberta-base-finetuned-panx-de-fr-en-it"
ner_pipeline = pipeline("token-classification", model=model_name, aggregation_strategy="simple")

# Example text (English, but you can use DE/FR/IT as well)
text = "Barack Obama was born in Hawaii and became President of the United States."

# Get NER predictions
entities = ner_pipeline(text)

# Display results
for entity in entities:
    print(f"{entity['word']} → {entity['entity_group']} ({entity['score']:.2f})")

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 64
eval_batch_size: 64
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	313	0.2470	0.7921
No log	2.0	626	0.2170	0.8318
No log	3.0	939	0.2148	0.8380

Framework versions

Transformers 4.50.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1