distilgpt2-finetuned-github_cybersecurity_READMEs
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.1579
- F1: 0.0127
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 6.1863 | 1.0 | 232 | 5.8725 | 0.0142 |
| 5.7221 | 2.0 | 464 | 5.4602 | 0.0131 |
| 5.4834 | 3.0 | 696 | 5.1579 | 0.0127 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2