distilbert-base-uncased-finetuned-char
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: 1.5972
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: 256
- eval_batch_size: 256
- 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 |
|---|---|---|---|
| 2.1436 | 0.85 | 500 | 1.8943 |
| 1.8911 | 1.71 | 1000 | 1.8065 |
| 1.8073 | 2.56 | 1500 | 1.7359 |
| 1.7668 | 3.41 | 2000 | 1.6907 |
| 1.733 | 4.27 | 2500 | 1.6564 |
| 1.7104 | 5.12 | 3000 | 1.6499 |
| 1.6915 | 5.97 | 3500 | 1.6258 |
| 1.6772 | 6.83 | 4000 | 1.6089 |
| 1.6617 | 7.68 | 4500 | 1.5982 |
| 1.6563 | 8.53 | 5000 | 1.6035 |
| 1.649 | 9.39 | 5500 | 1.5764 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3