--- library_name: transformers base_model: microsoft/graphcodebert-base tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: CodeDetect-GraphCodeBERT-T1 results: [] --- # CodeDetect-GraphCodeBERT-T1 This model is a fine-tuned version of [microsoft/graphcodebert-base](https://huggingface.co/microsoft/graphcodebert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1113 - Accuracy: 0.9755 - F1: 0.9755 - Precision: 0.9757 - Recall: 0.9752 ## 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: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - 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 - lr_scheduler_warmup_steps: 0.1 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| | 0.0787 | 1.0 | 16897 | 0.0718 | 0.9729 | 0.9728 | 0.9727 | 0.9730 | | 0.0604 | 2.0 | 33794 | 0.0699 | 0.9751 | 0.9750 | 0.9754 | 0.9747 | | 0.0441 | 3.0 | 50691 | 0.0785 | 0.9749 | 0.9748 | 0.9753 | 0.9745 | | 0.0324 | 4.0 | 67588 | 0.0934 | 0.9761 | 0.9760 | 0.9761 | 0.9759 | | 0.0206 | 5.0 | 84485 | 0.1113 | 0.9755 | 0.9755 | 0.9757 | 0.9752 | ### Framework versions - Transformers 5.13.1 - Pytorch 2.11.0+cu130 - Datasets 4.0.0 - Tokenizers 0.22.2