mbert-argumentClassification-german

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mbert-argumentClassification-german

This model is a fine-tuned version of fromdeath2morning/mbert-argumentClassification-german on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1482
• eval_model_preparation_time: 0.0027
• eval_accuracy: 0.9820
• eval_w_accuracy: 0.8700
• eval_classification_report: {'None': {'precision': 0.8752886836027713, 'recall': 0.8732718894009217, 'f1-score': 0.8742791234140715, 'support': 434.0}, 'S': {'precision': 0.9912280701754386, 'recall': 0.9940903901685582, 'f1-score': 0.9926571668063705, 'support': 14891.0}, 'A': {'precision': 0.9159049360146252, 'recall': 0.8978494623655914, 'f1-score': 0.9067873303167421, 'support': 558.0}, 'P': {'precision': 0.8871794871794871, 'recall': 0.8425324675324676, 'f1-score': 0.8642797668609492, 'support': 616.0}, 'accuracy': 0.9819989090247894, 'macro avg': {'precision': 0.9174002942430806, 'recall': 0.9019360523668848, 'f1-score': 0.9095008468495334, 'support': 16499.0}, 'weighted avg': {'precision': 0.9817461664382559, 'recall': 0.9819989090247894, 'f1-score': 0.981846092319441, 'support': 16499.0}}
• eval_hamming_loss: 0.0180
• eval_runtime: 9.2876
• eval_samples_per_second: 105.194
• eval_steps_per_second: 13.243
• step: 0

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: 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 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2