xlm-r-argumentClassification-turkish

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

• eval_loss: 0.5293
• eval_model_preparation_time: 0.0068
• eval_accuracy: 0.9423
• eval_w_accuracy: 0.1629
• eval_classification_report: {'None': {'precision': 0.14754098360655737, 'recall': 0.18, 'f1-score': 0.16216216216216217, 'support': 50.0}, 'S': {'precision': 0.9633755069919486, 'recall': 0.9806507271382795, 'f1-score': 0.9719363605826488, 'support': 16228.0}, 'A': {'precision': 0.1590909090909091, 'recall': 0.23863636363636365, 'f1-score': 0.19090909090909092, 'support': 176.0}, 'P': {'precision': 0.4340659340659341, 'recall': 0.1381118881118881, 'f1-score': 0.20954907161803712, 'support': 572.0}, 'accuracy': 0.9423235052272995, 'macro avg': {'precision': 0.4260183334388373, 'recall': 0.3843497447216328, 'f1-score': 0.3836391713179847, 'support': 17026.0}, 'weighted avg': {'precision': 0.9348831487684356, 'recall': 0.9423235052272995, 'f1-score': 0.9358718099735024, 'support': 17026.0}}
• eval_runtime: 9.1166
• eval_samples_per_second: 104.535
• eval_steps_per_second: 13.163
• 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 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2