metadata
base_model: microsoft/unixcoder-base
library_name: peft
license: apache-2.0
metrics:
- accuracy
- f1
- precision
- recall
tags:
- generated_from_trainer
model-index:
- name: CodeGenDetect-Unixcoder_Lora
results: []
CodeGenDetect-Unixcoder_Lora
This model is a fine-tuned version of microsoft/unixcoder-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0266
- Accuracy: 0.9927
- F1: 0.9927
- Precision: 0.9927
- Recall: 0.9927
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0349 | 1.02 | 4000 | 0.0342 | 0.9887 | 0.9887 | 0.9887 | 0.9887 |
| 0.0244 | 2.05 | 8000 | 0.0279 | 0.9916 | 0.9916 | 0.9916 | 0.9916 |
| 0.0234 | 3.07 | 12000 | 0.0260 | 0.9923 | 0.9923 | 0.9923 | 0.9923 |
| 0.0249 | 4.1 | 16000 | 0.0266 | 0.9927 | 0.9927 | 0.9927 | 0.9927 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.5.1+rocm6.2
- Datasets 2.21.0
- Tokenizers 0.15.2