xlm-r-argumentClassification-german

• eval_loss: 0.5888
• eval_model_preparation_time: 0.0082
• eval_accuracy: 0.9382
• eval_w_accuracy: 0.3797
• eval_classification_report: {'None': {'precision': 0.10743801652892562, 'recall': 0.26, 'f1-score': 0.15204678362573099, 'support': 50.0}, 'S': {'precision': 0.9771763532052881, 'recall': 0.9656149864431847, 'f1-score': 0.9713612695264071, 'support': 16228.0}, 'A': {'precision': 0.08780487804878048, 'recall': 0.20454545454545456, 'f1-score': 0.12286689419795221, 'support': 176.0}, 'P': {'precision': 0.5533769063180828, 'recall': 0.44405594405594406, 'f1-score': 0.492725509214355, 'support': 572.0}, 'accuracy': 0.9381534124280512, 'macro avg': {'precision': 0.4314490385252693, 'recall': 0.46855409626114586, 'f1-score': 0.43475011414111137, 'support': 17026.0}, 'weighted avg': {'precision': 0.9511908263592384, 'recall': 0.9381534124280512, 'f1-score': 0.9441041105195157, 'support': 17026.0}}
• eval_runtime: 8.8895
• eval_samples_per_second: 107.206
• eval_steps_per_second: 13.499
• step: 0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: 3.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2