4luc/codebert-code-clone-detector
094
1---2base_model: microsoft/codebert-base3tags:4- generated_from_trainer5metrics:6- accuracy7- precision8- recall9- f110model-index:11- name: codebert-code-clone-detector12 results: []13license: mit14pipeline_tag: sentence-similarity15---16 17 18 19# codebert-code-clone-detector20 21This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on a Code Clone Benchmark dataset.22See this [github repository](https://github.com/LucK1Y/CodeCloneBERT) for more information.23It achieves the following results on the evaluation set:24- Loss: 0.345225- Accuracy: 0.952526- Precision: 0.954427- Recall: 0.949628- F1: 0.952029 30## Model description31 32More information needed33 34## Intended uses & limitations35 36More information needed37 38## Training and evaluation data39 40More information needed41 42## Training procedure43 44### Training hyperparameters45 46The following hyperparameters were used during training:47- learning_rate: 2e-0548- train_batch_size: 1649- eval_batch_size: 1650- seed: 4251- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0852- lr_scheduler_type: linear53- num_epochs: 1554 55### Training results56 57| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |58|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|59| 0.3416 | 0.49 | 33 | 0.1724 | 0.9417 | 0.9828 | 0.9048 | 0.9421 |60| 0.221 | 0.97 | 66 | 0.2768 | 0.925 | 1.0 | 0.8571 | 0.9231 |61| 0.0929 | 1.46 | 99 | 0.2469 | 0.9583 | 1.0 | 0.9206 | 0.9587 |62| 0.1696 | 1.94 | 132 | 0.2142 | 0.95 | 0.9524 | 0.9524 | 0.9524 |63| 0.0818 | 2.43 | 165 | 0.4142 | 0.925 | 1.0 | 0.8571 | 0.9231 |64| 0.0676 | 2.91 | 198 | 0.3539 | 0.9333 | 0.9508 | 0.9206 | 0.9355 |65 66 67### Framework versions68 69- Transformers 4.39.370- Pytorch 2.1.271- Datasets 2.18.072- Tokenizers 0.15.2