CodeDetect-BERT-T2
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6532
- Accuracy: 0.5548
- F1: 0.5115
- Precision: 0.5100
- Recall: 0.5203
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 |
|---|---|---|---|---|---|---|---|
| 1.2780 | 1.0 | 13235 | 1.2988 | 0.5366 | 0.4938 | 0.5137 | 0.5308 |
| 1.0070 | 2.0 | 26470 | 1.3334 | 0.5470 | 0.5079 | 0.5153 | 0.5355 |
| 0.7668 | 3.0 | 39705 | 1.4235 | 0.5521 | 0.5082 | 0.5106 | 0.5232 |
| 0.5886 | 4.0 | 52940 | 1.5582 | 0.5537 | 0.5077 | 0.5057 | 0.5197 |
| 0.4668 | 5.0 | 66175 | 1.6532 | 0.5548 | 0.5115 | 0.5100 | 0.5203 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu130
- Datasets 4.0.0
- Tokenizers 0.22.2