xlm-roberta-base-finetuned-panx-all

This model is a fine-tuned version of xlm-roberta-base on the XTREME dataset, specifically on the PAN-X subset for the following languages:

• German (PAN-X.de)
• French (PAN-X.fr)
• Italian (PAN-X.it)
• English (PAN-X.en)

It achieves the following results on the evaluation set:

• Loss: 0.1728
• F1: 0.8567

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 24
• eval_batch_size: 24
• 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
0.2989	1.0	835	0.2149	0.8014
0.1552	2.0	1670	0.1750	0.8470
0.1025	3.0	2505	0.1728	0.8567

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.0