xlmr_german_immigration2

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: 0.3185
• Accuracy: 0.9077
• 1-f1: 0.8571
• 1-recall: 0.8372
• 1-precision: 0.8780
• Balanced Acc: 0.8899

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 with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.3106	1.0	5	0.2904	0.9	0.8434	0.8140	0.875	0.8782
0.2247	2.0	10	0.3269	0.9	0.8471	0.8372	0.8571	0.8841
0.2308	3.0	15	0.3185	0.9077	0.8571	0.8372	0.8780	0.8899

Framework versions

• Transformers 4.56.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4