--- library_name: transformers license: mit base_model: dbmdz/bert-base-turkish-cased tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: pelin_5e-05_4_5_detect results: [] --- # pelin_5e-05_4_5_detect This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6034 - Precision: 0.7120 - Recall: 0.5589 - F1: 0.6262 - Accuracy: 0.9156 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | 0.1818 | 1.0 | 675 | 0.1941 | 0.6067 | 0.1957 | 0.2959 | 0.9474 | | 0.1014 | 2.0 | 1350 | 0.2050 | 0.6282 | 0.3551 | 0.4537 | 0.9533 | | 0.053 | 3.0 | 2025 | 0.2312 | 0.4938 | 0.4312 | 0.4603 | 0.9539 | | 0.0333 | 4.0 | 2700 | 0.3004 | 0.5417 | 0.4239 | 0.4756 | 0.9536 | | 0.0095 | 5.0 | 3375 | 0.3057 | 0.4609 | 0.4275 | 0.4436 | 0.9502 | ### Framework versions - Transformers 4.48.2 - Pytorch 2.6.0+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0