README.md

metadata

license: mit
tags:
  - generated_from_trainer
datasets:
  - xtreme
metrics:
  - f1
model-index:
  - name: xlm-roberta-base-finetuned-panx-fr
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: xtreme
          type: xtreme
          config: PAN-X.fr
          split: train
          args: PAN-X.fr
        metrics:
          - name: F1
            type: f1
            value: 0.8366320026836633

xlm-roberta-base-finetuned-panx-fr

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: 0.3026
• F1: 0.8366

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	286	0.3632	0.7838
No log	2.0	572	0.3108	0.8160
No log	3.0	858	0.3026	0.8366

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2