distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5736
- Matthews Correlation: 0.5463
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.5222 | 1.0 | 535 | 0.5322 | 0.3973 |
| 0.3484 | 2.0 | 1070 | 0.5036 | 0.4986 |
| 0.2366 | 3.0 | 1605 | 0.5736 | 0.5463 |
| 0.1815 | 4.0 | 2140 | 0.7577 | 0.5294 |
| 0.1337 | 5.0 | 2675 | 0.8006 | 0.5449 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3