mbert-argumentClassification-welsh

• eval_loss: 0.1412
• eval_model_preparation_time: 0.0029
• eval_accuracy: 0.9820
• eval_w_accuracy: 0.7694
• eval_classification_report: {'None': {'precision': 0.6216216216216216, 'recall': 0.46, 'f1-score': 0.5287356321839081, 'support': 50.0}, 'S': {'precision': 0.991504555528195, 'recall': 0.9924821296524525, 'f1-score': 0.9919931017491993, 'support': 16228.0}, 'A': {'precision': 0.8214285714285714, 'recall': 0.6534090909090909, 'f1-score': 0.7278481012658228, 'support': 176.0}, 'P': {'precision': 0.7867768595041322, 'recall': 0.8321678321678322, 'f1-score': 0.8088360237892949, 'support': 572.0}, 'accuracy': 0.9820274873722542, 'macro avg': {'precision': 0.8053329020206301, 'recall': 0.7345147631823439, 'f1-score': 0.7643532147470562, 'support': 17026.0}, 'weighted avg': {'precision': 0.9817822624456962, 'recall': 0.9820274873722542, 'f1-score': 0.9817488727960451, 'support': 17026.0}}
• eval_hamming_loss: 0.0180
• eval_runtime: 9.307
• eval_samples_per_second: 102.396
• eval_steps_per_second: 12.894
• 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