CodeBERT-finetuned-PleIAs
This model is a fine-tuned version of huggingface/CodeBERTa-language-id on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9020
- F1: 0.7341
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 7 | 3.4985 | 0.2460 |
| No log | 2.0 | 14 | 2.7940 | 0.6174 |
| 1.8823 | 3.0 | 21 | 2.3548 | 0.6247 |
| 1.8823 | 4.0 | 28 | 2.1431 | 0.6736 |
| 1.3801 | 5.0 | 35 | 1.9985 | 0.6986 |
| 1.3801 | 6.0 | 42 | 1.8858 | 0.7233 |
| 0.0747 | 7.0 | 49 | 2.0295 | 0.7114 |
| 0.0747 | 8.0 | 56 | 1.8622 | 0.7378 |
| 0.0747 | 9.0 | 63 | 1.8878 | 0.7353 |
| 0.2302 | 10.0 | 70 | 1.9020 | 0.7341 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.22.1