xlm-r-argumentClassification-arabic

• eval_loss: 0.1573
• eval_model_preparation_time: 0.0064
• eval_accuracy: 0.9792
• eval_w_accuracy: 0.8662
• eval_classification_report: {'None': {'precision': 0.6238244514106583, 'recall': 0.8432203389830508, 'f1-score': 0.7171171171171171, 'support': 236.0}, 'S': {'precision': 0.99561900445653, 'recall': 0.9856058623397016, 'f1-score': 0.9905871301080319, 'support': 26747.0}, 'A': {'precision': 0.6913229018492176, 'recall': 0.8950276243093923, 'f1-score': 0.7800963081861958, 'support': 543.0}, 'P': {'precision': 0.8232984293193717, 'recall': 0.8523035230352304, 'f1-score': 0.8375499334221038, 'support': 738.0}, 'accuracy': 0.9791961505802435, 'macro avg': {'precision': 0.7835161967589443, 'recall': 0.8940393371668438, 'f1-score': 0.831337622208362, 'support': 28264.0}, 'weighted avg': {'precision': 0.9821690722924408, 'recall': 0.9791961505802435, 'f1-score': 0.9802638605593612, 'support': 28264.0}}
• eval_runtime: 9.3887
• eval_samples_per_second: 72.427
• eval_steps_per_second: 9.053
• 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