mbert-argumentClassification-arabic

• eval_loss: 0.1012
• eval_model_preparation_time: 0.0051
• eval_accuracy: 0.9835
• eval_w_accuracy: 0.8475
• eval_classification_report: {'None': {'precision': 0.7792207792207793, 'recall': 0.8, 'f1-score': 0.7894736842105263, 'support': 300.0}, 'S': {'precision': 0.9937323013026241, 'recall': 0.992420814479638, 'f1-score': 0.993076124893878, 'support': 26520.0}, 'A': {'precision': 0.8401122019635343, 'recall': 0.8706395348837209, 'f1-score': 0.8551034975017845, 'support': 688.0}, 'P': {'precision': 0.8430079155672823, 'recall': 0.8452380952380952, 'f1-score': 0.8441215323645971, 'support': 756.0}, 'accuracy': 0.9834772148315879, 'macro avg': {'precision': 0.864018299513555, 'recall': 0.8770746111503636, 'f1-score': 0.8704437097426965, 'support': 28264.0}, 'weighted avg': {'precision': 0.9836844764871073, 'recall': 0.9834772148315879, 'f1-score': 0.9835723189285899, 'support': 28264.0}}
• eval_hamming_loss: 0.0165
• eval_runtime: 7.311
• eval_samples_per_second: 93.011
• eval_steps_per_second: 11.626
• 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