metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
model-index:
- name: bert-practice-classifier
results: []
bert-practice-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: 0.5419
- Accuracy: 0.524
- Auc: 0.65
- Precision: 0.714
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: 5
- eval_batch_size: 5
- seed: 42
- 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 | Accuracy | Auc | Precision |
|---|---|---|---|---|---|---|
| 0.5815 | 1.0 | 34 | 0.6348 | 0.619 | 0.688 | 0.9 |
| 0.5744 | 2.0 | 68 | 0.5624 | 0.667 | 0.688 | 0.765 |
| 0.5532 | 3.0 | 102 | 0.5057 | 0.762 | 0.688 | 0.789 |
| 0.563 | 4.0 | 136 | 0.5677 | 0.571 | 0.688 | 0.769 |
| 0.514 | 5.0 | 170 | 0.5423 | 0.667 | 0.662 | 0.765 |
| 0.5349 | 6.0 | 204 | 0.5564 | 0.571 | 0.65 | 0.769 |
| 0.5298 | 7.0 | 238 | 0.5672 | 0.571 | 0.65 | 0.769 |
| 0.4964 | 8.0 | 272 | 0.5173 | 0.667 | 0.65 | 0.765 |
| 0.5083 | 9.0 | 306 | 0.5435 | 0.571 | 0.65 | 0.769 |
| 0.4908 | 10.0 | 340 | 0.5419 | 0.524 | 0.65 | 0.714 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0