--- library_name: transformers base_model: microsoft/codebert-base tags: - generated_from_trainer metrics: - accuracy - f1 - precision - recall model-index: - name: CodeDetect-CodeBERT-T2 results: [] --- # CodeDetect-CodeBERT-T2 This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.3390 - Accuracy: 0.6333 - F1: 0.5902 - Precision: 0.5843 - Recall: 0.6010 ## 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 | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| | 1.0683 | 1.0 | 13235 | 1.1079 | 0.5997 | 0.5594 | 0.5602 | 0.6005 | | 0.8459 | 2.0 | 26470 | 1.1190 | 0.6200 | 0.5819 | 0.5765 | 0.6089 | | 0.6554 | 3.0 | 39705 | 1.1410 | 0.6327 | 0.5882 | 0.5834 | 0.6053 | | 0.5130 | 4.0 | 52940 | 1.2600 | 0.6312 | 0.5878 | 0.5812 | 0.6018 | | 0.4146 | 5.0 | 66175 | 1.3390 | 0.6333 | 0.5902 | 0.5843 | 0.6010 | ### Framework versions - Transformers 5.13.1 - Pytorch 2.11.0+cu130 - Datasets 4.0.0 - Tokenizers 0.22.2