mbert-argumentClassification-basque

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

mbert-argumentClassification-basque

This model is a fine-tuned version of fromdeath2morning/mbert-argumentClassification-basque on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2679
• eval_model_preparation_time: 0.0026
• eval_accuracy: 0.9650
• eval_w_accuracy: 0.8165
• eval_classification_report: {'None': {'precision': 0.8066666666666666, 'recall': 0.8102678571428571, 'f1-score': 0.8084632516703786, 'support': 448.0}, 'S': {'precision': 0.9870826338369707, 'recall': 0.9849239216416175, 'f1-score': 0.986002096191918, 'support': 21491.0}, 'A': {'precision': 0.8446782178217822, 'recall': 0.8688733290897518, 'f1-score': 0.8566049576404142, 'support': 1571.0}, 'P': {'precision': 0.7245370370370371, 'recall': 0.7245370370370371, 'f1-score': 0.7245370370370371, 'support': 864.0}, 'accuracy': 0.9650036924591778, 'macro avg': {'precision': 0.8407411388406142, 'recall': 0.8471505362278159, 'f1-score': 0.843901835634937, 'support': 24374.0}, 'weighted avg': {'precision': 0.965281407674367, 'recall': 0.9650036924591778, 'f1-score': 0.9651304248158665, 'support': 24374.0}}
• eval_hamming_loss: 0.0350
• eval_runtime: 16.2454
• eval_samples_per_second: 110.739
• eval_steps_per_second: 13.85
• step: 0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• 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