mbert-argumentClassification-turkish

<!-- 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-turkish

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

• eval_loss: 0.2920
• eval_model_preparation_time: 0.0026
• eval_accuracy: 0.9575
• eval_w_accuracy: 0.6550
• eval_classification_report: {'None': {'precision': 0.7342657342657343, 'recall': 0.5614973262032086, 'f1-score': 0.6363636363636364, 'support': 187.0}, 'S': {'precision': 0.979598445595855, 'recall': 0.9848073792729246, 'f1-score': 0.982196006277396, 'support': 9215.0}, 'A': {'precision': 0.690677966101695, 'recall': 0.5659722222222222, 'f1-score': 0.6221374045801527, 'support': 288.0}, 'P': {'precision': 0.6856435643564357, 'recall': 0.7759103641456583, 'f1-score': 0.7279894875164258, 'support': 357.0}, 'accuracy': 0.9574997511695034, 'macro avg': {'precision': 0.77254642757993, 'recall': 0.7220468229610034, 'f1-score': 0.7421716336844028, 'support': 10047.0}, 'weighted avg': {'precision': 0.9563051035320027, 'recall': 0.9574997511695034, 'f1-score': 0.9564052968456904, 'support': 10047.0}}
• eval_hamming_loss: 0.0425
• eval_runtime: 8.8041
• eval_samples_per_second: 104.952
• eval_steps_per_second: 13.176
• 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