llm-selector
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7315
- Accuracy: 0.5048
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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 118 | 1.8920 | 0.3714 |
| No log | 2.0 | 236 | 1.7753 | 0.5143 |
| No log | 3.0 | 354 | 1.7671 | 0.4952 |
| No log | 4.0 | 472 | 1.7441 | 0.5048 |
| 1.8665 | 5.0 | 590 | 1.7315 | 0.5048 |
| 1.8665 | 6.0 | 708 | 1.7413 | 0.5048 |
| 1.8665 | 7.0 | 826 | 1.7378 | 0.4667 |
| 1.8665 | 8.0 | 944 | 1.7426 | 0.4667 |
| 1.7254 | 9.0 | 1062 | 1.7513 | 0.4476 |
| 1.7254 | 10.0 | 1180 | 1.7513 | 0.4476 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3