distilbert-base-uncased-finetuned-dataset
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: 0.5717
- Accuracy: 0.7602
- F1: 0.7490
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5754 | 1.0 | 2000 | 0.5628 | 0.7604 | 0.7439 |
| 0.4791 | 2.0 | 4000 | 0.5717 | 0.7602 | 0.7490 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.13.0+cu116
- Datasets 1.16.1
- Tokenizers 0.10.3