xlmr_dutch_immigration4

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: 0.3398
• Accuracy: 0.8923
• 1-f1: 0.8293
• 1-recall: 0.7907
• 1-precision: 0.8718
• Balanced Acc: 0.8666

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
0.3163	1.0	5	0.3140	0.9	0.8395	0.7907	0.8947	0.8724
0.4887	2.0	10	0.3272	0.8846	0.8193	0.7907	0.85	0.8609
0.2683	3.0	15	0.3398	0.8923	0.8293	0.7907	0.8718	0.8666

Framework versions

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