devops-command-classifier
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4777
- Accuracy: 0.5
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: 4
- eval_batch_size: 4
- 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
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8570 | 1.0 | 8 | 1.8103 | 0.0 |
| 1.7797 | 2.0 | 16 | 1.7721 | 0.125 |
| 1.7353 | 3.0 | 24 | 1.7278 | 0.25 |
| 1.5794 | 4.0 | 32 | 1.6794 | 0.25 |
| 1.4503 | 5.0 | 40 | 1.5916 | 0.25 |
| 1.2129 | 6.0 | 48 | 1.5365 | 0.25 |
| 1.2213 | 7.0 | 56 | 1.4938 | 0.5 |
| 1.1319 | 8.0 | 64 | 1.4777 | 0.5 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.12.1+cpu
- Datasets 5.0.0
- Tokenizers 0.22.2