mbert-argumentClassification-english

• eval_loss: 0.0561
• eval_model_preparation_time: 0.0113
• eval_accuracy: 0.9919
• eval_w_accuracy: 0.9563
• eval_classification_report: {'None': {'precision': 0.9585253456221198, 'recall': 0.9497716894977168, 'f1-score': 0.9541284403669725, 'support': 657.0}, 'S': {'precision': 0.9965192556562096, 'recall': 0.9961636258196904, 'f1-score': 0.9963414090037032, 'support': 22417.0}, 'A': {'precision': 0.9510961214165261, 'recall': 0.9632792485055508, 'f1-score': 0.9571489181162495, 'support': 1171.0}, 'P': {'precision': 0.9528301886792453, 'recall': 0.9517078916372202, 'f1-score': 0.9522687094873306, 'support': 849.0}, 'accuracy': 0.991910416832709, 'macro avg': {'precision': 0.9647427278435252, 'recall': 0.9652306138650446, 'f1-score': 0.9649718692435638, 'support': 25094.0}, 'weighted avg': {'precision': 0.9919267432249308, 'recall': 0.991910416832709, 'f1-score': 0.9919162058032194, 'support': 25094.0}}
• eval_hamming_loss: 0.0081
• eval_runtime: 26.3135
• eval_samples_per_second: 78.933
• eval_steps_per_second: 9.881
• 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 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2