xlm-r-argumentClassification-welsh

• eval_loss: 0.1047
• eval_model_preparation_time: 0.0052
• eval_accuracy: 0.9865
• eval_w_accuracy: 0.8296
• eval_classification_report: {'None': {'precision': 0.6666666666666666, 'recall': 0.48, 'f1-score': 0.5581395348837209, 'support': 50.0}, 'S': {'precision': 0.9945752681543583, 'recall': 0.9942075425191028, 'f1-score': 0.9943913713405239, 'support': 16228.0}, 'A': {'precision': 0.8366013071895425, 'recall': 0.7272727272727273, 'f1-score': 0.7781155015197568, 'support': 176.0}, 'P': {'precision': 0.8292682926829268, 'recall': 0.8916083916083916, 'f1-score': 0.8593091828138163, 'support': 572.0}, 'accuracy': 0.9864912486784917, 'macro avg': {'precision': 0.8317778836733736, 'recall': 0.7732721653500554, 'f1-score': 0.7974888976394545, 'support': 17026.0}, 'weighted avg': {'precision': 0.9864257064737608, 'recall': 0.9864912486784917, 'f1-score': 0.9863363873895917, 'support': 17026.0}}
• eval_runtime: 9.0066
• eval_samples_per_second: 105.811
• eval_steps_per_second: 13.324
• 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