xlmr_dutch_immigration3

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2108
• Accuracy: 0.9231
• 1-f1: 0.8684
• 1-recall: 0.7674
• 1-precision: 1.0
• Balanced Acc: 0.8837

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: 1e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.1857	1.0	5	0.1606	0.9462	0.9114	0.8372	1.0	0.9186
0.1012	2.0	10	0.1627	0.9308	0.8916	0.8605	0.925	0.9130
0.1712	3.0	15	0.2108	0.9231	0.8684	0.7674	1.0	0.8837

Framework versions

• Transformers 4.56.0.dev0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4