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: 0.5196
- Matthews Correlation: 0.5491
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 |
|---|---|---|---|---|
| 0.5224 | 1.0 | 535 | 0.5262 | 0.4063 |
| 0.351 | 2.0 | 1070 | 0.4991 | 0.4871 |
| 0.2369 | 3.0 | 1605 | 0.5196 | 0.5491 |
| 0.1756 | 4.0 | 2140 | 0.7817 | 0.5142 |
| 0.1268 | 5.0 | 2675 | 0.8089 | 0.5324 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Downloads last month
- 6
Dataset used to train BojanSimoski/distilbert-base-uncased-finetuned-cola
Evaluation results
- Matthews Correlation on glueself-reported0.549