distilbert-base-uncased-finetuned-20pc
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: 0.3326
- Accuracy: 0.8642
- F1: 0.4762
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 41 | 0.4428 | 0.8333 | 0.0 |
| No log | 2.0 | 82 | 0.4012 | 0.8333 | 0.0 |
| No log | 3.0 | 123 | 0.3619 | 0.8333 | 0.1818 |
| No log | 4.0 | 164 | 0.3488 | 0.8580 | 0.3784 |
| No log | 5.0 | 205 | 0.3326 | 0.8642 | 0.4762 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1